Tag Archives: Insights

Measuring characteristics of TCP connections at Internet scale

2025-10-29 Suleman Ahmad

Post Syndicated from Suleman Ahmad original https://blog.cloudflare.com/measuring-network-connections-at-scale/

Every interaction on the Internet—including loading a web page, streaming a video, or making an API call—starts with a connection. These fundamental logical connections consist of a stream of packets flowing back and forth between devices.

Various aspects of these network connections have captured the attention of researchers and practitioners for as long as the Internet has existed. The interest in connections even predates the label, as can be seen in the seminal 1991 paper, “Characteristics of wide-area TCP/IP conversations.” By any name, the Internet measurement community has been steeped in characterizations of Internet communication for decades, asking everything from “how long?” and “how big?” to “how often?” – and those are just to start.

Surprisingly, connection characteristics on the wider Internet are largely unavailable. While anyone can use tools (e.g., Wireshark) to capture data locally, it’s virtually impossible to measure connections globally because of access and scale. Moreover, network operators generally do not share the characteristics they observe — assuming that non-trivial time and energy is taken to observe them.

In this blog post, we move in another direction by sharing aggregate insights about connections established through our global CDN. We present characteristics of TCP connections—which account for about 70% of HTTP requests to Cloudflare—providing empirical insights that are difficult to obtain from client-side measurements alone.

Why connection characteristics matter

Characterizing system behavior helps us predict the impact of changes. In the context of networks, consider a new routing algorithm or transport protocol: how can you measure its effects? One option is to deploy the change directly on live networks, but this is risky. Unexpected consequences could disrupt users or other parts of the network, making a “deploy-first” approach potentially unsafe or ethically questionable.

A safer alternative to live deployment as a first step is simulation. Using simulation, a designer can get important insights about their scheme without having to build a full version. But simulating the whole Internet is challenging, as described by another highly seminal work, “Why we don’t know how to simulate the Internet”.

To run a useful simulation, we need it to behave like the real system we’re studying. That means generating synthetic data that mimics real-world behavior. Often, we do this by using statistical distributions — mathematical descriptions of how the real data behaves. But before we can create those distributions, we first need to characterize the data — to measure and understand its key properties. Only then can our simulation produce realistic results.

Unpacking the dataset

The value of any data depends on its collection mechanism. Every dataset has blind spots, biases, and limitations, and ignoring these can lead to misleading conclusions. By examining the finer details — how the data was gathered, what it represents, and what it excludes — we can better understand its reliability and make informed decisions about how to use it. Let’s take a closer look at our collected telemetry.

Dataset Overview. The data describes TCP connections, labeled Visitor to Cloudflare in the above diagram, which serve requests via HTTP 1.0, 1.1, and 2.0 that make up about 70% of all 84 million HTTP requests per second, on average, received at our global CDN servers.

Sampling. The passively collected snapshot of data is drawn from a uniformly sampled 1% of all TCP connections to Cloudflare between October 7 and October 15, 2025. Sampling takes place at each individual client-facing server to mitigate biases that may appear by sampling at the datacenter level.

Diversity. Unlike many large operators, whose traffic is primarily their own and dominated by a few services such as search, social media, or streaming video, the vast majority of Cloudflare’s workload comes from our customers, who choose to put Cloudflare in front of their websites to help protect, improve performance, and reduce costs. This diversity of customers brings a wide variety of web applications, services, and users from around the world. As a result, the connections we observe are shaped by a broad range of client devices and application-specific behaviors that are constantly evolving.

What we log. Each entry in the log consists of socket-level metadata captured via the Linux kernel’s TCP_INFO struct, alongside the SNI and the number of requests made during the connection. The logs exclude individual HTTP requests, transactions, and details. We restrict our use of the logs to connection metadata statistics such as duration and number of packets transmitted, as well as the number of HTTP requests processed.

Data capture. We have elected to represent ‘useful’ connections in our dataset that have been fully processed, by characterizing only those connections that close gracefully with a FIN packet. This excludes connections intercepted by attack mitigations, or that timeout, or that abort because of a RST packet.

Since a graceful close does not in itself indicate a ‘useful’ connection, we additionally require at least one successful HTTP request during the connection to filter out idle or non-HTTP connections from this analysis — interestingly, these make up 11% of all TCP connections to Cloudflare that close with a FIN packet.

If you’re curious, we’ve also previously blogged about the details of Cloudflare’s overall logging mechanism and post-processing pipeline.

Visualizing connection characteristics

Although networks are inherently dynamic and trends can change over time, the large-scale patterns we observe across our global infrastructure remain remarkably consistent over time. While our data offers a global view of connection characteristics, distributions can still vary according to regional traffic patterns.

In our visualizations we represent characteristics with cumulative distribution function (CDF) graphs, specifically their empirical equivalents. CDFs are particularly useful for gaining a macroscopic view of the distribution. They give a clear picture of both common and extreme cases in a single view. We use them in the illustrations below to make sense of large-scale patterns. To better interpret the distributions, we also employ log-scaled axes to account for the presence of extreme values common to networking data.

A long-standing question about Internet connections relates to “Elephants and Mice”; practitioners and researchers are entirely aware that most flows are small and some are huge, yet little data exists to inform the lines that divide them. This is where our presentation begins.

Packet Counts

Let’s start by taking a look at the distribution of the number of response packets sent in connections by Cloudflare servers back to the clients.

On the graph, the x-axis represents the number of response packets sent in log-scale, while the y-axis shows the cumulative fraction of connections below each packet count. The average response consists of roughly 240 packets, but the distribution is highly skewed. The median is 12 packets, which indicates that 50% of Internet connections consist of very few packets. Extending further to the 90th percentile, connections carry only 107 packets.

This stark contrast highlights the heavy-tailed nature of Internet traffic: while a few connections transport massive amounts of data—like video streams or large file transfers—most interactions are tiny, delivering small web objects, microservice traffic, or API responses.

The above plot breaks down the packet count distribution by HTTP protocol version. For HTTP/1.X (both HTTP 1.0 and 1.1 combined) connections, the median response consists of just 10 packets, and 90% of connections carry fewer than 63 response packets. In contrast, HTTP/2 connections show larger responses, with a median of 16 packets and a 90th percentile of 170 packets. This difference likely reflects how HTTP/2 multiplexes multiple streams over a single connection, often consolidating more requests and responses into fewer connections, which increases the total number of packets exchanged per connection. HTTP/2 connections also have additional control-plane frames and flow-control messages that increase response packet counts.

Despite these differences, the combined view displays the same heavy-tailed pattern: a small fraction of connections carry enormous volumes of data (elephant flows), extending to millions of packets, while most remain lightweight (mice flows).

So far, we’ve focused on the total number of packets sent from our servers to clients, but another important dimension of connection behavior is the balance between packets sent and received, illustrated below.

The x-axis shows the ratio of packets sent by our servers to packets received from clients, visualized as a CDF. Across all connections, the median ratio is 0.91, meaning that in half of connections, clients send slightly more packets than the server responds with. This excess of client-side packets primarily reflects TLS handshake initiation (ClientHello), HTTP control request headers, and data acknowledgements (ACKs), causing the client to typically transmit more packets than the server returns with the content payload — particularly for low-volume connections that dominate the distribution.

The mean ratio is higher, at 1.28, due to a long tail of client-heavy connections, such as large downloads typical of CDN workloads. Most connections fall within a relatively narrow range: 10% of connections have a ratio below 0.67, and 90% are below 1.85. However, the long-tailed behavior highlights the diversity of Internet traffic: extreme values arise from both upload-heavy and download-heavy connections. The variance of 3.71 reflects these asymmetric flows, while the bulk of connections maintain a roughly balanced upload-to-download exchange.

Bytes sent

Another dimension to look at the data is using bytes sent by our servers to clients, which captures the actual volume of data delivered over each connection. This metric is derived from tcpi_bytes_sent, also covering (re)transmitted segment payloads while excluding the TCP header, as defined in linux/tcp.h and aligned with RFC 4898 (TCP Extended Statistics MIB).

The plots above break down bytes sent by HTTP protocol version. The x-axis represents the total bytes sent by our servers over each connection. The patterns are generally consistent with what we observed in the packet count distributions.

For HTTP/1.X, the median response delivers 4.8 KB, and 90% of connections send fewer than 51 KB. In contrast, HTTP/2 connections show slightly larger responses, with a median of 6 KB and a 90th percentile of 146 KB. The mean is much higher—224 KB for HTTP/1.x and 390 KB for HTTP/2—reflecting a small number of very large transfers. These long-tailed extreme flows can reach tens of gigabytes per connection, while some very lightweight connections carry minimal payloads: the minimum for HTTP/1.X is 115 bytes and for HTTP/2 it is 202 bytes.

By making use of the tcpi_bytes_received metric, we can now look at the ratio of bytes sent to bytes received per connection to better understand the balance of data exchange. This ratio captures how asymmetric each connection is — essentially, how much data our servers send compared to what they receive from clients. Across all connections, the median ratio is 3.78, meaning that in half of all cases, servers send nearly four times more data than they receive. The average is far higher at 81.06, showing a strong long tail driven by download-heavy flows. Again we see the heavy long-tailed distribution, a small fraction of extreme cases push the ratio into the millions, with more extreme values of data transfers towards clients.

Connection duration

While packet and byte counts capture how much data is exchanged, connection duration provides insight into how that exchange unfolds over time.

The CDF above shows the distribution of connection durations (lifetimes) in seconds. A reminder that the x-axis is log-scale. Across all connections, the median duration is just 4.7 seconds, meaning half of connections complete in under five seconds. The mean is much higher at 96 seconds, reflecting a small number of long-lived connections that skew the average. Most connections fall within a window of 0.1 seconds (10th percentile) to 300 seconds (90th percentile). We also observe some extremely long-lived connections lasting multiple days, possibly maintained via keep-alives for connection reuse without hitting our default idle timeout limits. These long-lived connections typically represent persistent sessions or multimedia traffic, while the majority of web traffic remains short, bursty, and transient.

Request counts

A single connection can carry multiple HTTP requests for web traffic. This reveals patterns about connection multiplexing.

The above shows the number of HTTP requests (in log-scale) that we see on a single connection, broken down by HTTP protocol version. Right away, we can see that for both HTTP/1.X (mean 3 requests) and HTTP/2 (mean 8 requests) connections, the median number of requests is just 1, reinforcing the prevalence of limited connection reuse. However, because HTTP/2 supports multiplexing multiple streams over a single connection, the 90th percentile rises to 10 requests, with occasional extreme cases carrying thousands of requests, which can be amplified due to connection coalescing. In contrast, HTTP/1.X connections have much lower request counts. This aligns with protocol design: HTTP/1.0 followed a “one request per connection” philosophy, while HTTP/1.1 introduced persistent connections — even combining both versions, it’s rare to see HTTP/1.X connections carrying more than two requests at the 90th percentile.

The prevalence of short-lived connections can be partly explained by automated clients or scripts that tend to open new connections rather than maintaining long-lived sessions. To explore this intuition, we split the data between traffic originating from data centers (likely automated) and typical user traffic (user-driven), using client ASNs as a proxy.

The plot above shows that non-DC (user-driven) traffic has slightly higher request counts per connection, consistent with browsers or apps fetching multiple resources over a single persistent connection, with a mean of 5 requests and a 90th percentile of 5 requests per connection. In contrast, DC-originated traffic has a mean of roughly 3 requests and a 90th percentile of 2, validating our expectation. Despite these differences, the median number of requests remains 1 for both groups highlighting that, regardless of origin of connections, most are genuinely brief.

Inferring path characteristics from connection-level data

Connection-level measurements can also provide insights into underlying path characteristics. Let’s examine this in more detail.

Path MTU

The maximum transmission unit (MTU) along the network path is often referred to as the Path MTU (PMTU). PMTU determines the largest packet size that can traverse a connection without fragmentation or packet drop, affecting throughput, efficiency, and latency. The Linux TCP stack on our servers tracks the largest segment size that can be sent without fragmentation along the path for a connection, as part of Path MTU discovery.

From that data we saw that the median (and the 90th percentile!) PMTU was 1500 bytes, which aligns with the typical Ethernet MTU and is considered standard for most Internet paths. Interestingly, the 10th percentile sits at 1,420 bytes, reflecting cases where paths include network links with slightly smaller MTUs—common in some VPNs, IPv6tov4 tunnels, or older networking equipment that impose stricter limits to avoid fragmentation. At the extreme, we have seen MTU as small as 552 bytes for IPv4 connections which relates to the minimum allowed PMTU value by the Linux kernel.

Initial congestion window

A key parameter in transport protocols is the congestion window (CWND), which is the number of packets that can be transmitted without waiting for an acknowledgement from the receiver. We call these packets or bytes “in-flight.” During a connection, the congestion window evolves dynamically throughout a connection.

However, the initial congestion window (ICWND) at the start of a data transfer can have an outsized impact, especially for short-lived connections, which dominate Internet traffic as we’ve seen above. If the ICWND is set too low, small and medium transfers take additional round-trip times to reach bottleneck bandwidth, slowing delivery. Conversely, if it’s too high, the sender risks overwhelming the network, causing unnecessary packet loss and retransmissions — potentially for all connections that share the bottleneck link.

A reasonable estimate of the ICWND can be taken as the congestion window size at the instant the TCP sender transitions out of slow start. This transition marks the point at which the sender shifts from exponential growth to congestion-avoidance, having inferred that further growth may risk congestion. The figure below shows the distribution of congestion window sizes at the moment slow start exits — as calculated by BBR. The median is roughly 464 KB, which corresponds to about 310 packets per connection with a typical 1,500-byte MTU, while extreme flows carry tens of megabytes in flight. This variance reflects the diversity of TCP connections and the dynamically evolving nature of the networks carrying traffic.

It’s important to emphasize that these values reflect a mix of network paths, including not only paths between Cloudflare and end users, but also between Cloudflare and neighboring datacenters, which are typically well provisioned and offer higher bandwidth.

Our initial inspection of the above distribution left us doubtful, because the values seem very high. We then realized the numbers are an artifact of behaviour specific to BBR, in which it sets the congestion window higher than its estimate of the path’s available capacity, bandwidth delay product (BDP). The inflated value is by design. To prove the hypothesis, we re-plot the distribution from above in the figure below alongside BBR’s estimate of BDP. The difference is clear between BBR’s congestion window of unacknowledged packets and its BDP estimate.

The above plot adds the computed BDP values in context with connection telemetry. The median BDP comes out to be roughly 77 KB, which is roughly 50 packets. If we compare this to the congestion window distribution taken from above, we see BDP estimations from recently closed connections are much more stable.

We are using these insights to help identify reasonable initial congestion window sizes and the circumstances for them. Our own experiments internally make clear that ICWND sizes can affect performance by as much as 30-40% for smaller connections. Such insights will potentially help to revisit efforts to find better initial congestion window values, which has been a default of 10 packets for more than a decade.

Deeper understanding, better performance

We observed that Internet connections are highly heterogeneous, confirming decades-long observations of strong heavy-tail characteristics consistent with “elephants and mice” phenomenon. Ratios of upload to download bytes are unsurprising for larger flows, but surprisingly small for short flows, highlighting the asymmetric nature of Internet traffic. Understanding these connection characteristics continues to inform ways to improve connection performance, reliability, and user experience.

We will continue to build on this work, and plan to publish connection-level statistics on Cloudflare Radar so that others can similarly benefit.

Our work on improving our network is ongoing, and we welcome researchers, academics, interns, and anyone interested in this space to reach out at [email protected]. By sharing knowledge and working together, we all can continue to make the Internet faster, safer, and more reliable for everyone.

A framework for measuring Internet resilience

2025-10-28 Vasilis Giotsas

Post Syndicated from Vasilis Giotsas original https://blog.cloudflare.com/a-framework-for-measuring-internet-resilience/

On July 8, 2022, a massive outage at Rogers, one of Canada’s largest telecom providers, knocked out Internet and mobile services for over 12 million users. Why did this single event have such a catastrophic impact? And more importantly, why do some networks crumble in the face of disruption while others barely stumble?

The answer lies in a concept we call Internet resilience: a network’s ability not just to stay online, but to withstand, adapt to, and rapidly recover from failures.

It’s a quality that goes far beyond simple “uptime.” True resilience is a multi-layered capability, built on everything from the diversity of physical subsea cables to the security of BGP routing and the health of a competitive market. It’s an emergent property much like psychological resilience: while each individual network must be robust, true resilience only arises from the collective, interoperable actions of the entire ecosystem. In this post, we’ll introduce a data-driven framework to move beyond abstract definitions and start quantifying what makes a network resilient. All of our work is based on public data sources, and we’re sharing our metrics to help the entire community build a more reliable and secure Internet for everyone.

What is Internet resilience?

In networking, we often talk about “reliability” (does it work under normal conditions?) and “robustness” (can it handle a sudden traffic surge?). But resilience is more dynamic. It’s the ability to gracefully degrade, adapt, and most importantly, recover. For our work, we’ve adopted a pragmatic definition:

Internet resilience is the measurable capability of a national or regional network ecosystem to maintain diverse and secure routing paths in the face of challenges, and to rapidly restore connectivity following a disruption.

This definition links the abstract goal of resilience to the concrete, measurable metrics that form the basis of our analysis.

Local decisions have global impact

The Internet is a global system but is built out of thousands of local pieces. Every country depends on the global Internet for economic activity, communication, and critical services, yet most of the decisions that shape how traffic flows are made locally by individual networks.

In most national infrastructures like water or power grids, a central authority can plan, monitor, and coordinate how the system behaves. The Internet works very differently. Its core building blocks are Autonomous Systems (ASes), which are networks like ISPs, universities, cloud providers or enterprises. Each AS controls autonomously how it connects to the rest of the Internet, which routes it accepts or rejects, how it prefers to forward traffic, and with whom it interconnects. That’s why they’re called Autonomous Systems in the first place! There’s no global controller. Instead, the Internet’s routing fabric emerges from the collective interaction of thousands of independent networks, each optimizing for its own goals.

This decentralized structure is one of the Internet’s greatest strengths: no single failure can bring the whole system down. But it also makes measuring resilience at a country level tricky. National statistics can hide local structures that are crucial to global connectivity. For example, a country might appear to have many international connections overall, but those connections could be concentrated in just a handful of networks. If one of those fails, the whole country could be affected.

For resilience, the goal isn’t to isolate national infrastructure from the global Internet. In fact, the opposite is true: healthy integration with diverse partners is what makes both local and global connectivity stronger. When local networks invest in secure, redundant, and diverse interconnections, they improve their own resilience and contribute to the stability of the Internet as a whole.

This perspective shapes how we design and interpret resilience metrics. Rather than treating countries as isolated units, we look at how well their networks are woven into the global fabric: the number and diversity of upstream providers, the extent of international peering, and the richness of local interconnections. These are the building blocks of a resilient Internet.

Route hygiene: Keeping the Internet healthy

The Internet is constructed according to a layered model, by design, so that different Internet components and features can evolve independent of the others. The Physical layer stores, carries, and forwards, all the bits and bytes transmitted in packets between devices. It consists of cables, routers and switches, but also buildings that house interconnection facilities. The Application layer sits above all others and has virtually no information about the network so that applications can communicate without having to worry about the underlying details, for example, if a network is ethernet or Wi-Fi. The application layer includes web browsers, web servers, as well as caching, security, and other features provided by Content Distribution Networks (CDNs). Between the physical and application layers is the Network layer responsible for Internet routing. It is ‘logical’, consisting of software that learns about interconnection and routes, and makes (local) forwarding decisions that deliver packets to their destinations.

Good route hygiene works like personal hygiene: it prevents problems before they spread. The Internet relies on the Border Gateway Protocol (BGP) to exchange routes between networks, but BGP wasn’t built with security in mind. A single bad route announcement, whether by mistake or attack, can send traffic the wrong way or cause widespread outages.

Two practices help stop this: The RPKI (Resource Public Key Infrastructure) lets networks publish cryptographic proof that they’re allowed to announce specific IP prefixes. ROV (Route Origin Validation) checks those proofs before accepting routes.

Together, they act like passports and border checks for Internet routes, helping filter out hijacks and leaks early.

Hygiene doesn’t just happen in the routing table – it spans multiple layers of the Internet’s architecture, and weaknesses in one layer can ripple through the rest. At the physical layer, having multiple, geographically diverse cable routes ensures that a single cut or disaster doesn’t isolate an entire region. For example, distributing submarine landing stations along different coastlines can protect international connectivity when one corridor fails. At the network layer, practices like multi-homing and participation in Internet Exchange Points (IXPs) give operators more options to reroute traffic during incidents, reducing reliance on any single upstream provider. At the application layer, Content Delivery Networks (CDNs) and caching keep popular content close to users, so even if upstream routes are disrupted, many services remain accessible. Finally, policy and market structure also play a role: open peering policies and competitive markets foster diversity, while dependence on a single ISP or cable system creates fragility.

Resilience emerges when these layers work together. If one layer is weak, the whole system becomes more vulnerable to disruption.

The more networks adopt these practices, the stronger and more resilient the Internet becomes. We actively support the deployment of RPKI, ROV, and diverse routing to keep the global Internet healthy.

Measuring resilience is harder than it sounds

The biggest hurdle in measuring resilience is data access. The most valuable information, like internal network topologies, the physical paths of fiber cables, or specific peering agreements, is held by private network operators. This is the ground truth of the network.

However, operators view this information as a highly sensitive competitive asset. Revealing detailed network maps could expose strategic vulnerabilities or undermine business negotiations. Without access to this ground truth data, we’re forced to rely on inference, approximation, and the clever use of publicly available data sources. Our framework is built entirely on these public sources to ensure anyone can reproduce and build upon our findings.

Projects like RouteViews and RIPE RIS collect BGP routing data that shows how networks connect. Traceroute measurements reveal paths at the router level. IXP and submarine cable maps give partial views of the physical layer. But each of these sources has blind spots: peering links often don’t appear in BGP data, backup paths may remain hidden, and physical routes are hard to map precisely. This lack of a single, complete dataset means that resilience measurement relies on combining many partial perspectives, a bit like reconstructing a city map from scattered satellite images, traffic reports, and public utility filings. It’s challenging, but it’s also what makes this field so interesting.

Translating resilience into quantifiable metrics

Once we understand why resilience matters and what makes it hard to measure, the next step is to translate these ideas into concrete metrics. These metrics give us a way to evaluate how well different parts of the Internet can withstand disruptions and to identify where the weak points are. No single metric can capture Internet resilience on its own. Instead, we look at it from multiple angles: physical infrastructure, network topology, interconnection patterns, and routing behavior. Below are some of the key dimensions we use. Some of these metrics are inspired from existing research, like the ISOC Pulse framework. All described methods rely on public data sources and are fully reproducible. As a result, in our visualizations we intentionally omit country and region names to maintain focus on the methodology and interpretation of the results.

IXPs and colocation facilities

Networks primarily interconnect in two types of physical facilities: colocation facilities (colos), and Internet Exchange Points (IXPs) often housed within the colos. Although symbiotically linked, they serve distinct functions in a nation’s digital ecosystem. A colocation facility provides the foundational infrastructure —- secure space, power, and cooling – for network operators to place their equipment. The IXP builds upon this physical base to provide the logical interconnection fabric, a role that is transformative for a region’s Internet development and resilience. The networks that connect at these facilities are its members.

Metrics that reflect resilience include:

Number and distribution of IXPs, normalized by population or geography. A higher IXP count, weighted by population or geographic coverage, is associated with improved local connectivity.
Peering participation rates — the percentage of local networks connected to domestic IXPs. This metric reflects the extent to which local networks rely on regional interconnection rather than routing traffic through distant upstream providers.
Diversity of IXP membership, including ISPs, CDNs, and cloud providers, which indicates how much critical content is available locally, making it accessible to domestic users even if international connectivity is severely degraded.

Resilience also depends on how well local networks connect globally:

How many local networks peer at international IXPs, increasing their routing options
How many international networks peer at local IXPs, bringing content closer to users

A balanced flow in both directions strengthens resilience by ensuring multiple independent paths in and out of a region.

The geographic distribution of IXPs further enhances resilience. A resilient IXP ecosystem should be geographically dispersed to serve different regions within a country effectively, reducing the risk of a localized infrastructure failure from affecting the connectivity of an entire country. Spatial distribution metrics help evaluate how infrastructure is spread across a country’s geography or its population. Key spatial metrics include:

Infrastructure per Capita: This metric – inspired by teledensity – measures infrastructure relative to population size of a sub-region, providing a per-person availability indicator. A low IXP-per-population ratio in a region suggests that users there rely on distant exchanges, increasing the bit-risk miles.
Infrastructure per Area (Density): This metric evaluates how infrastructure is distributed per unit of geographic area, highlighting spatial coverage. Such area-based metrics are crucial for critical infrastructures to ensure remote areas are not left inaccessible.

These metrics can be summarized using the Location Quotient (LQ). The location quotient is a widely used geographic index that measures a region’s share of infrastructure relative to its share of a baseline (such as population or area).

For example, the figure above represents US states where a region hosts more or less infrastructure that is expected for its population, based on its LQ score. This statistic illustrates how even for the states with the highest number of facilities this number is still lower than would be expected given the population size of those states.

Economic-weighted metrics

While spatial metrics capture the physical distribution of infrastructure, economic and usage-weighted metrics reveal how infrastructure is actually used. These account for traffic, capacity, or economic activity, exposing imbalances that spatial counts miss. Infrastructure Utilization Concentration measures how usage is distributed across facilities, using indices like the Herfindahl–Hirschman Index (HHI). HHI sums the squared market shares of entities, ranging from 0 (competitive) to 10,000 (highly concentrated). For IXPs, market share is defined through operational metrics such as:

Peak/Average Traffic Volume (Gbps/Tbps): indicates operational significance
Number of Connected ASNs: reflects network reach
Total Port Capacity: shows physical scale

The chosen metric affects results. For example, using connected ASNs yields an HHI of 1,316 (unconcentrated) for a Central European country, whereas using port capacity gives 1,809 (moderately concentrated).

The Gini coefficient measures inequality in resource or traffic distribution (0 = equal, 1 = fully concentrated). The Lorenz curve visualizes this: a straight 45° line indicates perfect equality, while deviations show concentration.

The chart on the left suggests substantial geographical inequality in colocation facility distribution across the US states. However, the population-weighted analysis in the chart on the right demonstrates that much of that geographic concentration can be explained by population distribution.

Submarine cables

Internet resilience, in the context of undersea cables, is defined by the global network’s capacity to withstand physical infrastructure damage and to recover swiftly from faults, thereby ensuring the continuity of intercontinental data flow. The metrics for quantifying this resilience are multifaceted, encompassing the frequency and nature of faults, the efficiency of repair operations, and the inherent robustness of both the network’s topology and its dedicated maintenance resources. Such metrics include:

Number of landing stations, cable corridors, and operators. The goal is to ensure that national connectivity should withstand single failure events, be they natural disaster, targeted attack, or major power outage. A lack of diversity creates single points of failure, as highlighted by incidents in Tonga where damage to the only available cable led to a total outage.
Fault rates and mean time to repair (MTTR), which indicate how quickly service can be restored. These metrics measure a country’s ability to prevent, detect, and recover from cable incidents, focusing on downtime reduction and protection of critical assets. Repair times hinge on vessel mobilization and government permits, the latter often the main bottleneck.
Availability of satellite backup capacity as an emergency fallback. While cable diversity is essential, resilience planning must also cover worst-case outages. The Non-Terrestrial Backup System Readiness metric measures a nation’s ability to sustain essential connectivity during major cable disruptions. LEO and MEO satellites, though costlier and lower capacity than cables, offer proven emergency backup during conflicts or disasters. Projects like HEIST explore hybrid space-submarine architectures to boost resilience. Key indicators include available satellite bandwidth, the number of NGSO providers under contract (for diversity), and the deployment of satellite terminals for public and critical infrastructure. Tracking these shows how well a nation can maintain command, relief operations, and basic connectivity if cables fail.

Inter-domain routing

The network layer above the physical interconnection infrastructure governs how traffic is routed across the Autonomous Systems (ASes). Failures or instability at this layer – such as misconfigurations, attacks, or control-plane outages – can disrupt connectivity even when the underlying physical infrastructure remains intact. In this layer, we look at resilience metrics that characterize the robustness and fault tolerance of AS-level routing and BGP behavior.

AS Path Diversity measures the number and independence of AS-level routes between two points. High diversity provides alternative paths during failures, enabling BGP rerouting and maintaining connectivity. Low diversity leaves networks vulnerable to outages if a critical AS or link fails. Resilience depends on upstream topology.

Single-homed ASes rely on one provider, which is cheaper and simpler but more fragile.
Multi-homed ASes use multiple upstreams, requiring BGP but offering far greater redundancy and performance at higher cost.

The share of multi-homed ASes reflects an ecosystem’s overall resilience: higher rates signal greater protection from single-provider failures. This metric is easy to measure using public BGP data (e.g., RouteViews, RIPE RIS, CAIDA). Longitudinal BGP monitoring helps reveal hidden backup links that snapshots might miss.

Beyond multi-homing rates, the distribution of single-homed ASes per transit provider highlights systemic weak points. For each provider, counting customer ASes that rely exclusively on it reveals how many networks would be cut off if that provider fails.

The figure above shows Canadian transit providers for July 2025: the x-axis is total customer ASes, the y-axis is single-homed customers. Canada’s overall single-homing rate is 30%, with some providers serving many single-homed ASes, mirroring vulnerabilities seen during the 2022 Rogers outage, which disrupted over 12 million users.

While multi-homing metrics provide a valuable, static view of an ecosystem’s upstream topology, a more dynamic and nuanced understanding of resilience can be achieved by analyzing the characteristics of the actual BGP paths observed from global vantage points. These path-centric metrics move beyond simply counting connections to assess the diversity and independence of the routes to and from a country’s networks. These metrics include:

Path independence measures whether those alternative routes truly avoid shared bottlenecks. Multi-homing only helps if upstream paths are truly distinct. If two providers share upstream transit ASes, redundancy is weak. Independence can be measured with the Jaccard distance between AS paths. A stricter path disjointness score calculates the share of path pairs with no common ASes, directly quantifying true redundancy.
Transit entropy measures how evenly traffic is distributed across transit providers. High Shannon entropy signals a decentralized, resilient ecosystem; low entropy shows dependence on few providers, even if nominal path diversity is high.
International connectivity ratios evaluate the share of domestic ASes with direct international links. High percentages reflect a mature, distributed ecosystem; low values indicate reliance on a few gateways.

The figure below encapsulates the aforementioned AS-level resilience metrics into single polar pie charts. For the purpose of exposition we plot the metrics for infrastructure from two different nations with very different resilience profiles.

To pinpoint critical ASes and potential single points of failure, graph centrality metrics can provide useful insights. Betweenness Centrality (BC) identifies nodes lying on many shortest paths, but applying it to BGP data suffers from vantage point bias. ASes that provide BGP data to the RouteViews and RIS collectors appear falsely central. AS Hegemony, developed by Fontugne et al., corrects this by filtering biased viewpoints, producing a 0–1 score that reflects the true fraction of paths crossing an AS. It can be applied globally or locally to reveal Internet-wide or AS-specific dependencies.

Customer cone size developed by CAIDA offers another perspective, capturing an AS’s economic and routing influence via the set of networks it serves through customer links. Large cones indicate major transit hubs whose failure affects many downstream networks. However, global cone rankings can obscure regional importance, so country-level adaptations give more accurate resilience assessments.

Impact-Weighted Resilience Assessment

Not all networks have the same impact when they fail. A small hosting provider going offline affects far fewer people than if a national ISP does. Traditional resilience metrics treat all networks equally, which can mask where the real risks are. To address this, we use impact-weighted metrics that factor in a network’s user base or infrastructure footprint. For example, by weighting multi-homing rates or path diversity by user population, we can see how many people actually benefit from redundancy — not just how many networks have it. Similarly, weighting by the number of announced prefixes highlights networks that carry more traffic or control more address space.

This approach helps separate theoretical resilience from practical resilience. A country might have many multi-homed networks, but if most users rely on just one single-homed ISP, its resilience is weaker than it looks. Impact weighting helps surface these kinds of structural risks so that operators and policymakers can prioritize improvements where they matter most.

Metrics of network hygiene

Large Internet outages aren’t always caused by cable cuts or natural disasters — sometimes, they stem from routing mistakes or security gaps. Route hijacks, leaks, and spoofed announcements can disrupt traffic on a national scale. How well networks protect themselves against these incidents is a key part of resilience, and that’s where network hygiene comes in.

Network hygiene refers to the security and operational practices that make the global routing system more trustworthy. This includes:

Cryptographic validation, like RPKI, to prevent unauthorized route announcements. ROA Coverage measures the share of announced IPv4/IPv6 space with valid Route Origin Authorizations (ROAs), indicating participation in the RPKI ecosystem. ROV Deployment gauges how many networks drop invalid routes, but detecting active filtering is difficult. Policymakers can improve visibility by supporting independent measurements, data transparency, and standardized reporting.
Filtering and cooperative norms, where networks block bogus routes and follow best practices when sharing routing information.
Consistent deployment across both domestic networks and their international upstreams, since traffic often crosses multiple jurisdictions.

Strong hygiene practices reduce the likelihood of systemic routing failures and limit their impact when they occur. We actively support and monitor the adoption of these mechanisms, for instance through crowd-sourced measurements and public advocacy, because every additional network that validates routes and filters traffic contributes to a safer and more resilient Internet for everyone.

Another critical aspect of Internet hygiene is mitigating DDoS attacks, which often rely on IP address spoofing to amplify traffic and obscure the attacker’s origin. BCP-38, the IETF’s network ingress filtering recommendation, addresses this by requiring operators to block packets with spoofed source addresses, reducing a region’s role as a launchpad for global attacks. While BCP-38 does not prevent a network from being targeted, its deployment is a key indicator of collective security responsibility. Measuring compliance requires active testing from inside networks, which is carried out by the CAIDA Spoofer Project. Although the global sample remains limited, these metrics offer valuable insight into both the technical effectiveness and the security engagement of a nation’s network community, complementing RPKI in strengthening the overall routing security posture.

Measuring the collective security posture

Beyond securing individual networks through mechanisms like RPKI and BCP-38, strengthening the Internet’s resilience also depends on collective action and visibility. While origin validation and anti-spoofing reduce specific classes of threats, broader frameworks and shared measurement infrastructures are essential to address systemic risks and enable coordinated responses.

The Mutually Agreed Norms for Routing Security (MANRS) initiative promotes Internet resilience by defining a clear baseline of best practices. It is not a new technology but a framework fostering collective responsibility for global routing security. MANRS focuses on four key actions: filtering incorrect routes, anti-spoofing, coordination through accurate contact information, and global validation using RPKI and IRRs. While many networks implement these independently, MANRS participation signals a public commitment to these norms and to strengthening the shared security ecosystem.

Additionally, a region’s participation in public measurement platforms reflects its Internet observability, which is essential for fault detection, impact assessment, and incident response. RIPE Atlas and CAIDA Ark provide dense data-plane measurements; RouteViews and RIPE RIS collect BGP routing data to detect anomalies; and PeeringDB documents interconnection details, reflecting operational maturity and integration into the global peering fabric. Together, these platforms underpin observatories like IODA and GRIP, which combine BGP and active data to detect outages and routing incidents in near real time, offering critical visibility into Internet health and security.

Building a more resilient Internet, together

Measuring Internet resilience is complex, but it’s not impossible. By using publicly available data, we can create a transparent and reproducible framework to identify strengths, weaknesses, and single points of failure in any network ecosystem.

This isn’t just a theoretical exercise. For policymakers, this data can inform infrastructure investment and pro-competitive policies that encourage diversity. For network operators, it provides a benchmark to assess their own resilience and that of their partners. And for everyone who relies on the Internet, it’s a critical step toward building a more stable, secure, and reliable global network.

For more details of the framework, including a full table of the metrics and links to source code, please refer to the full paper: Regional Perspectives for Route Resilience in a Global Internet: Metrics, Methodology, and Pathways for Transparency published at TPRC23.

Network trends and natural language: Cloudflare Radar’s new Data Explorer & AI Assistant

2024-09-27 David Belson

Post Syndicated from David Belson original https://blog.cloudflare.com/radar-data-explorer-ai-assistant

Cloudflare Radar showcases global Internet traffic patterns, attack activity, and technology trends and insights. It is powered by data from Cloudflare’s global network, as well as aggregated and anonymized data from Cloudflare’s 1.1.1.1 public DNS Resolver, and is built on top of a rich, publicly accessible API. This API allows users to explore Radar data beyond the default set of visualizations, for example filtering by protocol, comparing metrics across multiple locations or autonomous systems, or examining trends over two different periods of time. However, not every user has the technical know-how to make a raw API query or process the JSON-formatted response.

Today, we are launching the Cloudflare Radar Data Explorer, which provides a simple Web-based interface to enable users to easily build more complex API queries, including comparisons and filters, and visualize the results. And as a complement to the Data Explorer, we are also launching an AI Assistant, which uses Cloudflare Workers AI to translate a user’s natural language statements or questions into the appropriate Radar API calls, the results of which are visualized in the Data Explorer. Below, we introduce the AI Assistant and Data Explorer, and also dig into how we used Cloudflare Developer Platform tools to build the AI Assistant.

Ask the AI Assistant

Sometimes, a user may know what they are looking for, but aren’t quite sure how to build the relevant API query by selecting from the available options and filters. (The sheer number may appear overwhelming.) In those cases, they can simply pose a question to the AI Assistant, like “Has there been an uptick in malicious email over the last week?” The AI Assistant makes a series of Workers AI and Radar API calls to retrieve the relevant data, which is visualized within seconds:

The AI Assistant pane is found on the right side of the page in desktop browsers, and appears when the user taps the “AI Assistant” button on a mobile browser. To use the AI Assistant, users just need to type their question into the “Ask me something” area at the bottom of the pane and submit it. A few sample queries are also displayed by default to provide examples of how and what to ask, and clicking on one submits it.

The submitted question is evaluated by the AI Assistant (more below on how that happens), and the resulting visualization is displayed in the Results section of the Data Explorer. In addition to the visualization of the results, the appropriate Data, Filter, and Compare options are selected in the Query section above the visualization, allowing the user to further tune or refine the results if necessary. The Keep current filters toggle within the AI Assistant pane allows users to build on the previous question. For example, with that toggle active, a user could ask “Traffic in the United States”, see the resultant graph, and then ask “Compare it with traffic in Mexico” to add Mexico’s data to the graph.

Building a query directly

For users that prefer a more hands-on approach, a wide variety of Radar datasets are available to explore, including traffic metrics, attacks, Internet quality, email security, and more. Once the user selects a dataset, the Breakdown By: dropdown is automatically populated with relevant options (if any), and Filter options are also dynamically populated. As the user selects additional options, the visualization in the Result section is automatically updated.

In addition to building the query of interest, Data Explorer also enables the user to compare the results, both against a specific date range and/or another location or autonomous system (AS). To compare results with the immediately previous period (the last seven days with the seven days before that, for instance), just toggle on the Previous period switch. Otherwise, clicking on the Date Range field brings up a calendar that enables the user to select a starting date — the corresponding date range is intelligently selected, based on the date range selected in the Filter section. To compare results across locations or ASNs, clicking on the “Location or ASN” field brings up a search box in which the user can enter a location (country/region) name, AS name, or AS number, with search results updating as the user types. Note that locations can be compared with other locations or ASes, and ASes can be compared with other ASes or locations. This enables a user, for example, to compare trends for their ISP with trends for their country.

Visualizing the results

Much of the value of Cloudflare Radar comes from its visualizations – the graphs, maps, and tables that illustrate the underlying data, and Data Explorer does not disappoint here. Depending on the dataset and filters selected, and the volume of data returned, results may be visualized in a time series graph, bar chart, treemap, or global choropleth map. The visualization type is determined automatically based on the contents of the API response. For example, the presence of countryalpha2 keys in the response means a choropleth map will be used, the presence of timestamps in the response means a line graph (“xychart”) should be shown, and more than 40 items in the response selects a treemap as the visualization type.

To illustrate the extended visualizations available in Data Explorer, the figure below is an expanded version of one that would normally be found on Radar’s Adoption & Usage page. The “standard” version of the graph plots the shares of the HTTP versions over the last seven days for the United States, as well as the summary share values. In this extended version of the graph generated in the Data Explorer, we compare data for the United States with HTTP version share data for AS701 (Verizon), for both the past seven days and the previous seven-day period. In addition to the comparisons plotted on the time series graph, the associated summary values are also compared in an accompanying bar chart. This comprehensive visualization makes comparisons easy.

For some combinations of datasets/filters/comparisons, time series graphs can get quite busy, with a significant number of lines being plotted. To isolate just a single line on the graph, double-click on the item in the legend. To add/remove additional lines back to/from the graph, single-click on the relevant legend item.

Similar to other visualizations on Radar, the resulting graphs or maps can be downloaded, copied, or embedded into another website or application. Simply click on the “Share” button above the visualization card to bring up the Share modal dialog. We hope to see these graphs shared in articles, blog posts, and presentations, and to see embedded visualizations with real-time data in your portals and operations centers!

Still want to use the API? No problem.

Although Data Explorer was designed to simplify the process of building, and viewing the results of, more complex API queries, we recognize that some users may still want to retrieve data directly from the API. To enable that, Data Explorer’s API section provides copyable API calls as a direct request URL and a cURL command. The raw data returned by the query is also available to copy or download as a JSON blob, for those users that want to save it locally, or paste it into another application for additional manipulation or analysis.

How we built the AI Assistant

Knowing all that AI is capable of these days, we thought that creating a system for an LLM to answer questions didn’t seem like an overly complex task. While there were some challenges, Cloudflare’s developer platform tools thankfully made it fairly straightforward.

LLM-assisted API querying

The main challenge we encountered in building the API Assistant was the large number of combinations of datasets and parameters that can potentially be visualized in the Data Explorer. There are around 100 API endpoints from which the data can be fetched, with most able to take multiple parameters.

There were a few potential approaches to getting started. One was to take a previously trained LLM and further train it with the API endpoint descriptions in order to have it return the output in the required structured format which would then be used to execute the API query. However, for the first version, we decided against this approach of fine-tuning, as we wanted to quickly test a few different models supported by Workers AI, and we wanted the flexibility to easily add or remove parameter combinations, as Data Explorer development was still under way. As such, we decided to start with prompt engineering, where all the endpoint-specific information is placed in the instructions sent to the LLM.

Putting the full detailed description of the API endpoints supported by the Data Explorer into the system prompt would be possible for an LLM with a larger context window (the number of tokens the model takes as input before generating output). Newer models are getting better with the needle in a haystack problem, which refers to the issue whereby LLMs do not retrieve information (the needle) equally well if it is placed in different positions within the long textual input (the haystack). However, it has been empirically shown that the position of information within the large context still matters. Additionally, many of the Radar API endpoints have quite similar descriptions, and putting all the descriptions in a single instruction could be more confusing for the model, and the processing time also increases with larger contexts. Based on this, we adopted the approach of having multiple inference calls to an LLM.

First, when the user enters a question, a Worker sends this question and a short general description of the available datasets to the LLM, asking it to determine the topic of the question. Then, based on the topic returned by the model, a system prompt is generated with the endpoint descriptions, including only those related to the topic. This prompt, along with the original question, is sent to the LLM asking it to select the appropriate endpoint and its specific parameters. At the same time, two parallel inference calls to the model are also made, one with the question and the system prompt related to the description of location parameters, and another with the description of time range parameters. Then, all three model outputs are put together and validated.

If the final output is a valid dataset and parameter combination, it is sent back to the Data Explorer, which executes the API query and displays the resulting visualization for the user. Different LLMs were tested for this task, and at the end, openhermes-2.5-mistral-7b, trained on code datasets, was selected as the best option. To give the model more context, not only is the user’s current question sent to the model, but the previous one and its response are as well, in case the next question asked by the user is related to the previous one. In addition, calls to the model are sent through Cloudflare’s AI Gateway, to allow for caching, rate limiting, and logging.

After the user is shown the result, they can indicate whether what was shown to them was useful or not by clicking the “thumbs up” or “thumbs down” icons in the response. This rating information is saved with the original question in D1, our serverless SQL database, so the results can be analyzed and applied to future AI Assistant improvements.

The full end-to-end data flow for the Cloudflare Radar AI Assistant is illustrated in the diagram below.

When the LLM doesn’t know the answer

In some cases, however, the LLM may not “know” the answer to the question posed by the user. If the model does not generate a valid final response, then the user is shown three alternative questions. The intent here is to guide the user into asking an answerable question — that is, a question that is answerable with data from Radar.

This is achieved using a previously compiled (static) list of various questions related to different Radar datasets. For each of these questions, their embedding is calculated using an embeddings model, and stored in our Vectorize vector database. “Embeddings” are numerical representations of textual data (vectors) capturing their semantic meaning and relationships, with similar text having vectors that are closer. When a user’s question does not generate a valid model response, the embedding of that question is calculated, and its vector is compared against all the stored vectors from the vector database, and the three most similar ones are selected. These three questions, determined to be similar to the user’s original question, are then shown to the user.

There are also cases when the LLM gives answers which do not correspond to what the user asked, as hallucinations are currently inevitable in LLMs, or when time durations are calculated inaccurately, as LLMs sometimes struggle with mathematical calculations. To help guard against this, AI Assistant responses are first validated against the API schema to confirm that the dataset and the parameter combination is valid. Additionally, Data Explorer dropdown options are automatically populated based on the AI Assistant’s response, and the chart titles are also automatically generated, so the user always knows exactly what data is shown in the visualization, even if it might not answer their actual question.

Looking ahead

We’re excited to enable more granular access to the rich datasets that currently power Cloudflare Radar. As we add new datasets in the future, such as DNS metrics, these will be available through Data Explorer and AI Assistant as well.

As noted above, Radar offers a predefined set of visualizations, and these serve as an excellent starting point for further exploration. We are adding links from each Radar visualization into Data Explorer, enabling users to further analyze the associated data to answer more specific questions. Clicking the “pie chart” icon next to a graph’s description brings up a Data Explorer page with the relevant metrics, options, and filters selected.

Correlating observations across two different metrics is another capability that we are also working on adding to Data Explorer. For example, if you are investigating an Internet disruption, you will be able to plot traffic trends and announced IP address space for a given country or autonomous system on the same graph to determine if both dropped concurrently.

But for now, use the Data Explorer and AI Assistant to go beyond what Cloudflare Radar offers, finding answers to your questions about what’s happening on the Internet. If you share Data Explorer visualizations on social media, be sure to tag us: @CloudflareRadar (X), noc.social/@cloudflareradar (Mastodon), and radar.cloudflare.com (Bluesky). You can also reach out on social media, or contact us via email, with suggestions for future Data Explorer and AI Assistant functionality.

How the Harris-Trump US presidential debate influenced Internet traffic

2024-09-11 João Tomé

Post Syndicated from João Tomé original https://blog.cloudflare.com/how-the-harris-trump-us-presidential-debate-influenced-internet-traffic

Much has changed in the 2024 United States presidential election since the June 27 debate between Donald Trump and Joe Biden, then the presumptive nominees for the November election. Now, over two months later, on September 10, the debate was between Kamala Harris, the Democratic nominee, and Donald Trump, the Republican nominee. In this post, we will explore the event’s impact on Internet traffic in specific states where there was a bigger impact than during the Biden-Trump debate, as well as examine cyberattacks, email phishing trends, and general DNS data on candidates, news, and election-related activity.

We’ve been tracking the 2024 elections globally through our blog and election report on Cloudflare Radar, covering some of the more than 60 national elections this year. Regarding the US elections, we have previously reported on trends surrounding the first Biden vs. Trump debate, the attempted assassination of Trump, the Republican National Convention, and the Democratic National Convention.

Typically, we have observed that election days don’t come with significant changes to Internet traffic, and the same is true for debates. Yet, debates can also draw attention that impacts traffic, especially when there is heightened anticipation. The 2024 debates were not only aired on broadcast and cable television, but also streamed on platforms like YouTube, increasing their reach and impact.

Key takeaways:

The September 10 Harris-Trump debate caused bigger drops in Internet traffic in the US than the Biden-Trump debate on June 27.
There was also a noticeable increase in DNS traffic to both Kamala Harris-related and Donald Trump-related domains, with Trump-related DNS traffic peaking around the start of the debate and Harris-related DNS traffic peaking after the debate ended, around the time Taylor Swift announced she was endorsing Harris.
We also observed increases in DNS traffic to US news media outlets and election-related domains right after the debate ended.
Donald Trump remains the candidate with the most mentions in email subjects and the highest percentages of emails classified as spam (26.7%) and malicious (2.4%). Since mid-August, there has been a slight increase in the percentage of spam and malicious emails mentioning Kamala Harris.

Traffic drop in the US

During the September 10, 2024, debate between Harris and Trump, hosted by ABC News at 21:00 EST (01:00 UTC) in Philadelphia, Pennsylvania, Cloudflare noted a trend similar to the Biden-Trump debate, with a clear drop in nationwide Internet requests, falling as much as 9% below the same time a week prior at 21:15 EST (01:15 UTC). At the end of the debate, around 22:45 EST (02:45 UTC), the drop was less evident, at just 2%. Traffic increased slightly just after the debate.

_{Note: there were two four-minute breaks during the debate, at around 22:00 and 22:30, and our data here has 15-minute granularity.}

There’s a clear difference between this second debate, with a drop of up to 9%, and the first one between Biden and Trump on June 27, when the traffic dropped just 2% below the same time a week prior. Interestingly, the biggest drop occurred at the same time in both debates, right after they started, at 21:15 EST (01:15 UTC).

Internet traffic dips across US states

Traffic shifts at the time of the debate, as compared to the previous week, can reveal more detail at a state-level perspective than at the country level. The map below summarizes traffic changes observed at a state level. A key observation is that traffic declines at a state level were much more pronounced during the Harris-Trump debate, than during the Biden-Trump debate in late June.

_{(Source: Cloudflare; created with Datawrapper)}

The most significant traffic drops were observed in Vermont (-25%), Montana (-22%), and Idaho (-19%). More populous states such as California (-11%), Texas (-10%), and New York (-14%) also experienced notable declines in traffic.

Just for comparison, here’s the state map from that June 27 Biden-Trump debate:

_{(Source: Cloudflare; created with Datawrapper)}

The initial minutes of the Harris-Trump debate triggered the largest traffic declines in most states, at least up until the first break, at around 21:30 ET (01:30 UTC).

In the next table, we provide a detailed breakdown of the same perspective shown on the US map ordered by the magnitude of the drop in traffic. We include the time of the biggest traffic drop compared to the previous week, at a 5-minute granularity, and also the percentage of the drop compared to the previous week. As noted above, the largest declines appeared to occur earlier in the debate.

State	Drop in traffic (%)	Local Time	UTC
Vermont	-25%	21:05 EDT	1:05
Montana	-22%	19:10 MDT	1:10
Idaho	-19%	19:10 MDT	1:10
Wyoming	-19%	19:15 MDT	1:15
North Dakota	-18%	20:15 CDT	1:15
Delaware	-15%	21:20 EDT	1:20
Illinois	-15%	20:20 CDT	1:20
Mississippi	-14%	20:05 CDT	1:05
New York	-14%	21:05 EDT	1:05
Rhode Island	-14%	21:45 EDT	1:45
West Virginia	-14%	21:15 EDT	1:15
Alabama	-13%	20:05 CDT	1:05
Georgia	-13%	21:20 EDT	1:20
South Carolina	-13%	21:15 EDT	1:15
Virginia	-13%	21:15 EDT	1:15
Colorado	-12%	19:45 MDT	1:45
Connecticut	-12%	21:05 EDT	1:05
Nevada	-12%	18:20 PDT	1:20
New Jersey	-12%	21:20 EDT	1:20
Alaska	-11%	17:15 AKDT	1:15
California	-11%	18:15 PDT	1:15
Florida	-11%	21:05 EDT	1:05
North Carolina	-11%	21:05 EDT	1:05
Wisconsin	-11%	20:20 CDT	1:20
Arkansas	-10%	20:05 CDT	1:05
District of Columbia	-10%	21:55 EDT	1:55
Missouri	-10%	20:25 CDT	1:25
Oregon	-10%	18:40 PDT	1:40
Pennsylvania	-10%	21:05 EDT	1:05
South Dakota	-10%	20:20 CDT	1:20
Texas	-10%	20:05 CDT	1:05
Maryland	-9%	21:20 EDT	1:20
Massachusetts	-9%	21:20 EDT	1:20
New Hampshire	-9%	21:05 EDT	1:05
Oklahoma	-9%	20:05 CDT	1:05
Arizona	-8%	18:15 MST	1:15
Indiana	-8%	21:05 EDT	1:05
Iowa	-8%	20:05 CDT	1:05
Kentucky	-8%	21:05 EDT	1:05
Maine	-8%	21:15 EDT	1:15
Nebraska	-8%	19:45 MDT	1:45
Kansas	-7%	20:25 CDT	1:25
Louisiana	-7%	20:20 CDT	1:20
Michigan	-7%	21:20 EDT	1:20
Minnesota	-7%	20:30 CDT	1:30
New Mexico	-7%	19:25 MDT	1:25
Washington	-7%	18:05 PDT	1:05
Hawaii	-6%	15:20 HST	1:20
Ohio	-6%	21:15 EDT	1:15
Tennessee	-6%	20:05 CDT	1:05
Utah	-6%	19:10 MDT	1:10

Swing state drops in traffic higher than first debate

The seven swing states that are said to be decisive in the election — Arizona, Georgia, Michigan, Nevada, North Carolina, Pennsylvania, and Wisconsin — each saw traffic drop between 8% and 13%, which is more than during the Biden-Trump debate (between 5% and 8% at that time). Here’s a more focused view of those swing states for easier visualization:

State	Drop in traffic	Local Time	UTC
Arizona	-8%	18:15 MST	1:15
Georgia	-13%	21:20 EDT	1:20
Michigan	-7%	21:20 EDT	1:20
Nevada	-12%	18:20 PDT	1:20
North Carolina	-11%	21:05 EDT	1:05
Pennsylvania	-10%	21:05 EDT	1:05
Wisconsin	-11%	20:20 CDT	1:20

DNS trends

Shifting our attention to domain trends, our 1.1.1.1 resolver data highlights a more targeted impact during and around the debate. Let’s start with Kamala Harris-related insights.

Harris and the Taylor Swift effect

Since July 21, the date of Biden’s withdrawal and endorsement of Harris, daily DNS traffic to Harris-related domains has significantly increased, with notable peaks on August 30 (the day after the Harris-Walz interview on CNN) and September 10 (the debate with Trump).

From an hourly perspective, the impact of the debate on Kamala Harris-related sites is evident, with increased DNS traffic throughout the day (September 10). The peak occurred at the debate’s start (21:00 ET / 01:00 UTC) with a 54% increase from the previous week, and again after it ended (23:00 ET / 03:00 UTC) with a 56% rise. This spike coincided with Taylor Swift’s endorsement of Kamala Harris.

Trump and the Elon Musk interview effect

Donald Trump, having a longer-standing campaign and websites compared to Kamala Harris, shows different trends. Aggregated daily DNS traffic to Trump-related domains has also increased in recent months. Significant peaks were observed on July 15 (two days after the assassination attempt), then during the Republican National Convention (August 19-22), with the highest spike occurring on August 12, following Elon Musk’s interview with Trump on X.

Hourly data shows the debate’s impact on Trump-related sites with a noticeable increase around the debate’s start (21:00 ET / 01:00 UTC), where DNS traffic was 46% higher than the previous week. This elevated traffic continued for a few hours, after the debate ended.

From news to election-related sites

Like previous US election-related events, the debate generated significant interest in US news organizations, leading to a rise in aggregated DNS traffic to general US news sites. This increase peaked during the debate at 22:00 ET (02:00 UTC), with DNS traffic 62% higher than the previous week. The elevated DNS traffic began before the debate and persisted afterward, with a 19% increase at 20:00 ET (00:00 UTC) and a 25% increase at 00:00 ET (04:00 UTC).

Microblogging social platforms like X or Threads outperformed their previous week’s traffic throughout the debate, peaking at 16% growth around 22:00 ET (02:00 UTC).

Additionally, there was a notable increase in DNS traffic to election-related websites, including official voting registration and election sites. During the morning of September 10 in the US, DNS traffic was 38% higher at 10:00 ET (14:00 UTC), with a significant spike at 23:00 ET (03:00 UTC) right after the debate, where DNS traffic surged by 76% compared to the previous week.

Harris-Trump: spam and malicious emails

From a cybersecurity perspective, trending events, topics, and individuals often attract more emails, including malicious, phishing, and spam messages. Our earlier analysis covered email trends involving “Joe Biden” and “Donald Trump” since January. We’ve since updated it to include Kamala Harris after the Democratic Convention.

From June 1, 2024, through August 21, Cloudflare’s Cloud Email Security service processed over 16 million emails that included the names “Donald Trump”, “Joe Biden”, or “Kamala Harris” in the subject, with 8.7 million referencing Trump, 4.8 million referencing Biden, and 3 million referencing Harris.

The chart below highlights a surge in emails mentioning Trump in mid-July, contrasting with a drop in the number of emails mentioning Biden in the subject and an increase in emails mentioning Harris.

Since July 21, following changes in the presumptive Democratic candidate, over 4.5 million emails mentioned “Donald Trump,” over 1.5 million mentioned “Joe Biden,” and around 2.8 million mentioned “Kamala Harris” in the subject. Of these, 26.7% of emails with Trump’s name were classified as spam, and 2.4% were classified as malicious. For Kamala Harris, 1.1% were classified as spam and 0.2% were classified as malicious, while Biden’s figures were 1.1% for spam and 0.1% for malicious.

Since mid-August, there has been a slight increase in the percentage of spam and malicious emails mentioning Kamala Harris. Trump remains the candidate with the most mentions in email subjects and the highest percentages of emails classified as spam and malicious.

September attacks on political and news sites

In our blog posts about several of the 2024 elections, we have noted that attacks on politically-related websites have remained a significant threat this year. In Europe, we’ve seen political parties and associated websites targeted around elections. We previously reported on DDoS attacks around the Republican National Convention and Democratic National Convention.

In our post about the Democratic National Convention, we showed that during late July and August, Cloudflare blocked DDoS attacks targeting three US politically related organizations, including a site associated with one of the major parties, with attacks occurring just before the Democratic Convention.

The largest DDoS attack recorded in recent days against politically-related websites targeted specifically a US political-party related website on September 4, peaking at 140,000 requests per second (rps) and lasting about 5 minutes.

But it’s not only US politically-related websites that could be the target of cyber attacks. News organizations are often attacked during relevant events, as we saw during the first year of the war in Ukraine, for example. Already in September, we’ve seen an example of a relevant US news organization that covers politics being the target of a DDoS attack on September 3, peaking at 343,000 requests per second (rps) and lasting about 5 minutes.

As highlighted in our Q2 DDoS report, most DDoS attacks are short-lived, as exemplified by the two mentioned attacks. Also, 81% of HTTP DDoS attacks peak at under 50,000 requests per second (rps), and only 7% reach between 100,000 and 250,000 rps. While a 140,000 rps attack might seem minor to Cloudflare, it can be devastating for websites not equipped to handle such high levels of traffic.

Conclusion

In this analysis of the Harris-Trump debate, we’ve observed that the September 10 debate caused bigger drops in traffic in the US than the Biden-Trump debate in late June. There was also a noticeable increase in DNS traffic to both Kamala Harris-related and Donald Trump-related domains, as well as to US news media outlets and election-related domains — in this case, right after the debate ended.

If you’re interested in more trends and insights about the Internet and elections, check out Cloudflare Radar, specifically our 2024 Elections Insights report. It will be updated throughout the year as elections (or election-related events) occur.

Internet insights on 2024 elections in the Netherlands, South Africa, Iceland, India, and Mexico

2024-06-07 João Tomé

Post Syndicated from João Tomé original https://blog.cloudflare.com/internet-insights-on-2024-elections-in-the-netherlands-south-africa-iceland-india-and-mexico

2024 is being called by the media “the” year of elections. More voters than ever are going to the polls in at least 60 countries for national elections, plus the 27 member states of the European Union. This includes eight of the world’s 10 most populous nations, impacting around half of the world’s population.

To track and analyze these significant global events, we’ve created the 2024 Election Insights report on Cloudflare Radar, which will be regularly updated as elections take place.

Our data shows that during elections, there is often a decrease in Internet traffic during polling hours, followed by an increase as results are announced. This trend has been observed before in countries like France and Brazil, and more recently in Mexico and India — where elections were held between April 19 and June 1 in seven phases. Some regions, like Comoros and Pakistan, have experienced government-directed Internet disruptions around election time.

Below, you’ll find a review of the trends we saw in elections in South Africa (May 29), to Mexico (June 2), India (April 19 – June 1) and Iceland (June 1). This includes election-related shifts in traffic, as well at attacks. For example, during the European Parliament election (June 6-9, 2024), DDoS attacks targeted Dutch political websites for two days, peaking at 73,000 requests per second.

We’ll also be keeping an eye on upcoming elections. The United Kingdom recently scheduled its general election for July 4, making it the latest addition to the electoral calendar.

Locations with national elections in 2024 (over 60, plus EU elections with 27 countries participating). Including local elections, over 100 countries will hold elections. In several countries, there will be multiple elections in 2024.

Dutch political websites hit by cyber attacks

Europe: 2024 European Parliament election (June 6-9)

As mentioned above, we recently published a blog post about the cyber attack on Dutch political-related websites. The 2024 European Parliament election started in the Netherlands on June 6, and continues through June 9 in the other 26 countries that are part of the European Union. Cloudflare observed DDoS attacks targeting multiple election or politically-related Internet properties on election day in the Netherlands, as well as the preceding day.

The main June 5 DDoS attack on one of the websites peaked at 14:13 UTC (16:13 local time), reaching 73,000 requests per second (rps) in an attack that lasted for a few hours. This attack is illustrated by the blue line in the graph below, which shows that it ramped slowly over the first half of the day, and then appeared to abruptly stop at 18:06. And on June 6, the main attack on the second website peaked at 11:01 UTC (13:01 local time) with 52,000 rps.

More information can be found in the dedicated blog post and the elections report.

A European Union perspective

In Europe, cyberattacks have been a significant issue. In March 2024, French government websites faced attacks of “unprecedented intensity,” according to a spokesperson. Just days earlier, on February 25, 2024, Cloudflare blocked a major DDoS attack on a French government website, which reached 420 million requests per hour and lasted over three hours.

Looking at government or state-related websites in the European Union in 2024, there have been several spikes in attacks targeting defense organizations, European courts, and educational institutions.

These incidents highlight the ongoing threat to critical infrastructure across Europe, with government sites frequently targeted by cyberattacks.

Mexicans go offline: early traffic drops on election day

Mexico: Presidential, Senate, and Chamber of Deputies elections (June 2)

General elections were held in Mexico on Sunday, June 2, 2024, resulting in the election of the first female president, Claudia Sheinbaum, from the Morena political party. Cloudflare data shows a typical election day pattern in Mexico, mirroring trends seen in other countries: when polling stations are open, HTTP requests dip below normal levels. On June 2, traffic decreased between 08:00 and 20:00 CST (14:00 and 02:00 UTC), gradually recovering afterward as polling stations closed at 18:00 CST. Throughout the day, traffic experienced drops of up to 11% at 09:30 and 13:00 CST, with daily traffic decreasing by 3%.

The first official results were released after 23:00 (05:00 UTC in the chart above), coinciding with an 8% increase in traffic compared to the previous week. This growth peaked at 01:30 (07:30 UTC), with a 14% surge in HTTP requests, maintaining elevated levels until 07:30 in Mexico.

A similar trend was observed at the state level, with the period between 10:00 CST and 14:00 being the one with the most significant drop in traffic, with voting taking place all over the country.

(We provide a full table of the biggest drops in traffic and the specific time of that drop on election day by Mexican state in our Radar 2024 Election Insights report).

Website trends: traffic spikes from news and election results

Switching to domain trends, DNS traffic (using our 1.1.1.1 resolver) to election results sites in Mexico grew by almost 116x compared to the previous week, peaking at 20:00 CST (02:00 UTC), and remained up to 80x higher, until 23:00 CST (05:00 UTC).

Examining news media outlets, there was noticeable growth in DNS queries on Election Day, June 2, with traffic significantly higher than the previous week in the early morning. By 20:00 CST (02:00 UTC), traffic surged to 1.8x higher, then skyrocketed to a 4.8x increase by 23:00 CST (05:00 UTC), reaching a peak at 01:00 CST (07:00 UTC) with a staggering 1057% more DNS traffic than the previous week.

Attacks: early May election-related DDoS spike

We didn’t see any unusual attacks targeting Mexico before the election, except for one targeting a state electoral organization. A specific DDoS attack on May 6 targeted a state electoral organization, reaching 130 million HTTP requests per hour, with a peak of 113,000 requests per second at 09:12 CST (15:12 UTC). The attack lasted about 30 minutes.

India’s elections: 44 days of traffic dips and mobile spikes

India: General election (April 19 – June 1)

In India, general elections were held from April 19 to June 1, 2024 in seven phases, with incumbent Prime Minister Narendra Modi winning by a smaller margin than in the previous election. More than 968 million people out of a population of 1.4 billion were eligible to vote, and there was a 66% turnout, making it the largest election in human history.

Not all states voted on the same days, leading to mixed HTTP request patterns. On April 18, the day before the first election day, traffic was 10% higher than the previous week, marking the biggest increase of the year, something we’ve seen in other elections.

Some of the seven election days had a nationwide impact. Not all states in India voted on the same days. However, days with more constituencies or populous states participating saw bigger traffic changes. For example, May 7, 2024, saw 11 states, including the most populous ones, voting. This day (highlighted in the next chart) experienced the biggest nationwide drop in traffic, with a 6% decrease compared to the previous week. May 20 and May 25 also saw drops of 4% and 3%, respectively.

The period between 15:30 and 19:30 local time (10:00 – 14:00 UTC) typically witnessed the most significant drop in traffic on election days.

In Uttar Pradesh, the most populous Indian state, the first day of elections on April 19 saw the biggest drop (9%). May 20 and 25, with more constituencies voting, also experienced significant traffic drops, especially May 20, with traffic lower than usual between 10:30 and 22:30 UTC (05:00 – 17:00 UTC), and a 5% daily drop compared to the previous week.

In Maharashtra, home to the capital Mumbai, May 20 saw the most impact, with a 17% drop in daily traffic compared to the previous week. On this day, traffic hit its lowest point at 14:30 local time (09:00 UTC), with a drop of approximately 20%.

(We provide a full table of the states in India with the biggest drop in daily traffic over the several election days in our Radar 2024 Election Insights report).

Mobile devices first in India

India is a mobile-first country, with most election days during the week. On weekends, mobile devices are used more, especially on Sundays when they can reach 69% of all traffic. During the week, usage is typically between 61% and 62%. On election days, mobile device usage increased to around 64%.

Saturday, June 1, 2024, the last election day, was the Saturday of the year in India with the highest daily mobile device traffic percentage, reaching 68% (typically around 65-66%).

The increase in mobile device usage on election days was more noticeable during the day, particularly between 10:00 and 13:00 local time (04:30 – 07:30 UTC). May 13 and May 20 showed the biggest differences compared to typical days, reaching up to 62% during those times. In India, mobile usage during weekends is higher at night than during the day.

Attacks

Since April 2024, Cloudflare hasn’t observed any unusual or potentially election-related attacks targeting India. However, there have been large attacks on online financial services, consulting firms, and online casinos. The most targeted industries during this period have been Information Technology and Services, BFSI (Banking, Financial Services, and Insurance), and Gaming/Gambling.

Iceland’s 2024 election: impact before and after extended voting day

Iceland: Presidential election (June 1)

Iceland held its presidential election on Saturday, June 1, 2024, and Halla Tómasdóttir was elected as the new president. She is the second woman to become president in Iceland and the fourth woman to hold a top leadership position, including prime ministers.

In terms of HTTP requests, there wasn’t much change during election day. This might be because polling stations in Iceland were open from 09:00 to 22:00 local time (same as UTC), spreading out the impact. However, traffic increased the days before and after the election.

On May 31, the day before the election, daily traffic in Iceland was 7% lower than the previous week. It remained stable on election day and increased by 14% on Sunday when results were announced. This increase was only surpassed by two days in 2024:

May 2: +17%, driven by a 9% drop the previous week due to the national holiday, the first day of summer.
March 19: +16%, due to a volcanic eruption that led to a state of emergency, evacuations, and road closures.

Looking deeper into election day traffic with 15-minute granularity, traffic was around 12% lower between 14:00 and 16:00 local time (same as UTC), with the biggest drop, 20%, at 15:30.

Mobile devices usage changes

June 2 and June 1, election day, were also the days in 2024 with the highest percentage of mobile device usage in Iceland, at 47% and 45%, respectively. June 1’s percentage is tied with March 2, the day the famous Blue Lagoon was evacuated due to nearby seismic activity suggesting an “imminent” volcanic eruption, and January 1, the first day of the year.

Attacks

Cloudflare didn’t observe any relevant attacks during the election period targeting Iceland and its Internet properties. Since the beginning of April 2024, the most attacked industries were Retail and Gaming.

South Africa: traffic surges pre-voting, 16% decrease during voting

South Africa: 2024 general election (May 29)

On general election day in South Africa, which took place on Wednesday, May 29, 2024, HTTP requests dipped while polling stations were open. Traffic remained lower than usual from around 05:30 local time (03:30 UTC), with a 16% drop observed at 05:45 (03:45 UTC) and a 14% decrease by 11:00 (09:00 UTC), persisting until 18:00 (16:00 UTC).

However, as shown in the chart above, the night leading up to the election saw a traffic surge, peaking at a 25% increase around midnight local time (22:00 UTC). Following the election, traffic rose compared to the previous week, with a 6% increase at 23:30 local time and a 12% to 8% rise around 04:00 and 09:00 local time (02:00 – 07:00 UTC) on May 30.

Daily traffic overall was 6% lower than the previous week, with mobile device usage increasing to 63%, compared to 57% the previous week.

Attacks: news under attack

Cloudflare didn’t detect any major threats targeting government or election-related online platforms. However, in the lead-up to election day, on May 7, a significant DDoS attack targeted a major news site in South Africa, with 773 million daily requests. This attack peaked at 16:06 local time (14:06 UTC) with 54,000 requests per second and continued in the following days.

Geopolitics are here to stay

Elections, geopolitical changes, and disputes impact the online world. Our DDoS threat report for Q1 2024 gives a few recent examples. One notable case was the 466% surge in DDoS attacks on Sweden after its acceptance into the NATO alliance, mirroring the pattern observed during Finland’s NATO accession in 2023.

Real-world conflicts and wars often lead to Internet pattern changes, disruptions, or cyberattacks. For instance, during the first year of the war in Ukraine, and more recently, Cloudflare’s Cloudforce One thwarted a phishing attack by the Russia-aligned threat actor FlyingYeti. Our recent Project Galileo blog post also details how we protected Meduza, an independent news outlet focused on Russia, from online attacks in late 2023.

We’ve also reported (1, 2) on Internet changes, disruptions, and increased cyberattacks following the start of the Israel-Hamas war on October 7, 2023.
If you want to follow more trends and insights about the Internet and elections in particular, you can check Cloudflare Radar, and more specifically our new 2024 Elections Insights report, that we’re updating as national and European elections take place throughout the year.

Secure your unprotected assets with Security Center: quick view for CISOs

2024-03-05 Alexandra Moraru

Post Syndicated from Alexandra Moraru original https://blog.cloudflare.com/security-insights-quick-ciso-view

We understand that one of the significant hurdles faced by our customers, especially larger organizations, is obtaining a clear view of the deployment of Cloudflare services throughout their vast and complex infrastructures. The question isn’t just whether Cloudflare is deployed, but whether it’s fully optimized across every asset and service. Addressing this challenge head-on, we’re rolling out a new feature set designed to provide better visibility and control over your security posture.

The problem we are addressing

The core problem we’re tackling is the growing complexity of cyber threats and the expanding attack surface, which complicates maintaining a strong security posture for our customers.

It’s not uncommon for organizations to deploy a variety of security solutions, including ours, without fully optimizing and implementing their configurations. This results in a false sense of security, underutilized investments and, more critically, exposed vulnerabilities. Our customers frequently express concerns about not having a clear picture of their security posture across their entire infrastructure, uncertain if critical assets are adequately protected or if specific Cloudflare security features could be better leveraged.

We want to bring users comprehensive visibility into their security configurations and the state of their deployments across Cloudflare’s suite of products. By providing actionable insights into underconfigured areas, unassigned resources, or unutilized features, we aim to close the security gaps and enhance the overall defense mechanisms of our customers’ digital ecosystems. This improvement is not just about leveraging technology but about promoting a culture of proactive security management, where every piece of the digital infrastructure is consistently and optimally protected.

How we’re solving this inside Security Center

More than two years ago, we took on the mission to consolidate our extensive suite of security products, security expertise, and our unique insights into Internet threats into one comprehensive solution — the Cloudflare Security Center. Launched with the vision to simplify attack surface management and make advanced security intelligence actionable for organizations of all sizes, Security Center has since become the one-stop quick view to evaluate your security posture.

Today, we build on this foundation to address a pain point for many of our large customers: ensuring complete Cloudflare protection across their entire digital infrastructure.

Our latest update in the Security Center focuses on delivering detailed insights into Cloudflare’s deployment status across your digital assets. This encompasses identifying applications where critical services like WAF, Access, and other security protection tools might not be fully configured or optimized, thereby weakening your security posture.

In addition to these insights, we are introducing a quick view within Security Center Insights, designed to offer CISOs and security teams a quick and comprehensive view of their current Cloudflare product configurations at any given moment, along with recommendations for enhancements, under the Security optimization snapshot on the dashboard.

Leveraging these new insights, Cloudflare users can now take proactive steps to close any gaps in their security framework. By offering a granular view of where specific Cloudflare services can be better utilized, we’re not just solving a visibility problem — we’re delivering actionable security intelligence. This means decisions can be made swiftly, ensuring that your defenses not only keep pace with, but stay ahead of, potential threats.

For instance, we’ll highlight if WAF is deployed on only a portion of your zones, where Email Security could be leveraged, or if certain assets are unprotected by Access controls. We’re also making it easier for you to see if you are missing any critical setup like Page Shield, ensuring the product is configured, so you are not just one step closer to becoming compliant with standards like PCI DSS, but are also protected against evolving threats. We are outlining newly discovered API endpoints that require your attention as well.

Finally, users can now export their Security Insights using our public API, and will soon be able to do the same directly from the Cloudflare Dashboard, with a simple click of a button!

Accessing Security Center Insights

Security Center Insights is available to all Cloudflare dashboard users that are Administrators of their Cloudflare account.

Regardless of the size or scope of your deployment, our goal is to empower every user with the tools needed to achieve a robust security posture, which they can continuously influence by improving existing configurations, adding new solutions, and discovering new vulnerabilities.

Future Security Center roadmap

We’re constantly adding other relevant security insights to help improve your security posture, covering exposed infrastructure, insecure configurations, optimisations, new products, and more, including the ability to easily export these for reporting purposes. Moreover, stay tuned for a completely new reporting platform that will automatically deliver curated and contextualized security insights directly into your inbox — showcasing the power of Cloudflare’s security portfolio. The periodic reports will be complemented by a personalized interactive in-dashboard reporting experience.

Check out your security insights under your account’s Security Center now and take action to improve your security posture with Cloudflare!

If you would like to join us in building the Security Center or other exciting Cloudflare products, see our open positions and learn more about life@Cloudflare.

DDoS threat report for 2023 Q4

2024-01-09 Omer Yoachimik http://blog.cloudflare.com/author/omer/

Post Syndicated from Omer Yoachimik http://blog.cloudflare.com/author/omer/ original https://blog.cloudflare.com/ddos-threat-report-2023-q4

Welcome to the sixteenth edition of Cloudflare’s DDoS Threat Report. This edition covers DDoS trends and key findings for the fourth and final quarter of the year 2023, complete with a review of major trends throughout the year.

What are DDoS attacks?

DDoS attacks, or distributed denial-of-service attacks, are a type of cyber attack that aims to disrupt websites and online services for users, making them unavailable by overwhelming them with more traffic than they can handle. They are similar to car gridlocks that jam roads, preventing drivers from getting to their destination.

There are three main types of DDoS attacks that we will cover in this report. The first is an HTTP request intensive DDoS attack that aims to overwhelm HTTP servers with more requests than they can handle to cause a denial of service event. The second is an IP packet intensive DDoS attack that aims to overwhelm in-line appliances such as routers, firewalls, and servers with more packets than they can handle. The third is a bit-intensive attack that aims to saturate and clog the Internet link causing that ‘gridlock’ that we discussed. In this report, we will highlight various techniques and insights on all three types of attacks.

Previous editions of the report can be found here, and are also available on our interactive hub, Cloudflare Radar. Cloudflare Radar showcases global Internet traffic, attacks, and technology trends and insights, with drill-down and filtering capabilities for zooming in on insights of specific countries, industries, and service providers. Cloudflare Radar also offers a free API allowing academics, data sleuths, and other web enthusiasts to investigate Internet usage across the globe.

To learn how we prepare this report, refer to our Methodologies.

Key findings

In Q4, we observed a 117% year-over-year increase in network-layer DDoS attacks, and overall increased DDoS activity targeting retail, shipment and public relations websites during and around Black Friday and the holiday season.
In Q4, DDoS attack traffic targeting Taiwan registered a 3,370% growth, compared to the previous year, amidst the upcoming general election and reported tensions with China. The percentage of DDoS attack traffic targeting Israeli websites grew by 27% quarter-over-quarter, and the percentage of DDoS attack traffic targeting Palestinian websites grew by 1,126% quarter-over-quarter — as the military conflict between Israel and Hamas continues.
In Q4, there was a staggering 61,839% surge in DDoS attack traffic targeting Environmental Services websites compared to the previous year, coinciding with the 28th United Nations Climate Change Conference (COP 28).

For an in-depth analysis of these key findings and additional insights that could redefine your understanding of current cybersecurity challenges, read on!

Hyper-volumetric HTTP DDoS attacks

2023 was the year of uncharted territories. DDoS attacks reached new heights — in size and sophistication. The wider Internet community, including Cloudflare, faced a persistent and deliberately engineered campaign of thousands of hyper-volumetric DDoS attacks at never before seen rates.

These attacks were highly complex and exploited an HTTP/2 vulnerability. Cloudflare developed purpose-built technology to mitigate the vulnerability’s effect and worked with others in the industry to responsibly disclose it.

As part of this DDoS campaign, in Q3 our systems mitigated the largest attack we’ve ever seen — 201 million requests per second (rps). That’s almost 8 times larger than our previous 2022 record of 26 million rps.

Largest HTTP DDoS attacks as seen by Cloudflare, by year

Growth in network-layer DDoS attacks

After the hyper-volumetric campaign subsided, we saw an unexpected drop in HTTP DDoS attacks. Overall in 2023, our automated defenses mitigated over 5.2 million HTTP DDoS attacks consisting of over 26 trillion requests. That averages at 594 HTTP DDoS attacks and 3 billion mitigated requests every hour.

Despite these astronomical figures, the amount of HTTP DDoS attack requests actually declined by 20% compared to 2022. This decline was not just annual but was also observed in 2023 Q4 where the number of HTTP DDoS attack requests decreased by 7% YoY and 18% QoQ.

On the network-layer, we saw a completely different trend. Our automated defenses mitigated 8.7 million network-layer DDoS attacks in 2023. This represents an 85% increase compared to 2022.

In 2023 Q4, Cloudflare’s automated defenses mitigated over 80 petabytes of network-layer attacks. On average, our systems auto-mitigated 996 network-layer DDoS attacks and 27 terabytes every hour. The number of network-layer DDoS attacks in 2023 Q4 increased by 175% YoY and 25% QoQ.

HTTP and Network-layer DDoS attacks by quarter

DDoS attacks increase during and around COP 28

In the final quarter of 2023, the landscape of cyber threats witnessed a significant shift. While the Cryptocurrency sector was initially leading in terms of the volume of HTTP DDoS attack requests, a new target emerged as a primary victim. The Environmental Services industry experienced an unprecedented surge in HTTP DDoS attacks, with these attacks constituting half of all its HTTP traffic. This marked a staggering 618-fold increase compared to the previous year, highlighting a disturbing trend in the cyber threat landscape.

This surge in cyber attacks coincided with COP 28, which ran from November 30th to December 12th, 2023. The conference was a pivotal event, signaling what many considered the ‘beginning of the end’ for the fossil fuel era. It was observed that in the period leading up to COP 28, there was a noticeable spike in HTTP attacks targeting Environmental Services websites. This pattern wasn’t isolated to this event alone.

Looking back at historical data, particularly during COP 26 and COP 27, as well as other UN environment-related resolutions or announcements, a similar pattern emerges. Each of these events was accompanied by a corresponding increase in cyber attacks aimed at Environmental Services websites.

In February and March 2023, significant environmental events like the UN’s resolution on climate justice and the launch of United Nations Environment Programme’s Freshwater Challenge potentially heightened the profile of environmental websites, possibly correlating with an increase in attacks on these sites.

This recurring pattern underscores the growing intersection between environmental issues and cyber security, a nexus that is increasingly becoming a focal point for attackers in the digital age.

DDoS attacks and Iron Swords

It’s not just UN resolutions that trigger DDoS attacks. Cyber attacks, and particularly DDoS attacks, have long been a tool of war and disruption. We witnessed an increase in DDoS attack activity in the Ukraine-Russia war, and now we’re also witnessing it in the Israel-Hamas war. We first reported the cyber activity in our report Cyber attacks in the Israel-Hamas war, and we continued to monitor the activity throughout Q4.

Operation “Iron Swords” is the military offensive launched by Israel against Hamas following the Hamas-led 7 October attack. During this ongoing armed conflict, we continue to see DDoS attacks targeting both sides.

DDoS attacks targeting Israeli and Palestinian websites, by industry

Relative to each region’s traffic, the Palestinian territories was the second most attacked region by HTTP DDoS attacks in Q4. Over 10% of all HTTP requests towards Palestinian websites were DDoS attacks, a total of 1.3 billion DDoS requests — representing a 1,126% increase in QoQ. 90% of these DDoS attacks targeted Palestinian Banking websites. Another 8% targeted Information Technology and Internet platforms.

Similarly, our systems automatically mitigated over 2.2 billion HTTP DDoS requests targeting Israeli websites. While 2.2 billion represents a decrease compared to the previous quarter and year, it did amount to a larger percentage out of the total Israel-bound traffic. This normalized figure represents a 27% increase QoQ but a 92% decrease YoY. Notwithstanding the larger amount of attack traffic, Israel was the 77th most attacked region relative to its own traffic. It was also the 33rd most attacked by total volume of attacks, whereas the Palestinian territories was 42nd.

Of those Israeli websites attacked, Newspaper & Media were the main target — receiving almost 40% of all Israel-bound HTTP DDoS attacks. The second most attacked industry was the Computer Software industry. The Banking, Financial Institutions, and Insurance (BFSI) industry came in third.

On the network layer, we see the same trend. Palestinian networks were targeted by 470 terabytes of attack traffic — accounting for over 68% of all traffic towards Palestinian networks. Surpassed only by China, this figure placed the Palestinian territories as the second most attacked region in the world, by network-layer DDoS attack, relative to all Palestinian territories-bound traffic. By absolute volume of traffic, it came in third. Those 470 terabytes accounted for approximately 1% of all DDoS traffic that Cloudflare mitigated.

Israeli networks, though, were targeted by only 2.4 terabytes of attack traffic, placing it as the 8th most attacked country by network-layer DDoS attacks (normalized). Those 2.4 terabytes accounted for almost 10% of all traffic towards Israeli networks.

When we turned the picture around, we saw that 3% of all bytes that were ingested in our Israeli-based data centers were network-layer DDoS attacks. In our Palestinian-based data centers, that figure was significantly higher — approximately 17% of all bytes.

On the application layer, we saw that 4% of HTTP requests originating from Palestinian IP addresses were DDoS attacks, and almost 2% of HTTP requests originating from Israeli IP addresses were DDoS attacks as well.

Main sources of DDoS attacks

In the third quarter of 2022, China was the largest source of HTTP DDoS attack traffic. However, since the fourth quarter of 2022, the US took the first place as the largest source of HTTP DDoS attacks and has maintained that undesirable position for five consecutive quarters. Similarly, our data centers in the US are the ones ingesting the most network-layer DDoS attack traffic — over 38% of all attack bytes.

HTTP DDoS attacks originating from China and the US by quarter

Together, China and the US account for a little over a quarter of all HTTP DDoS attack traffic in the world. Brazil, Germany, Indonesia, and Argentina account for the next twenty-five percent.

These large figures usually correspond to large markets. For this reason, we also normalize the attack traffic originating from each country by comparing their outbound traffic. When we do this, we often get small island nations or smaller market countries that a disproportionate amount of attack traffic originates from. In Q4, 40% of Saint Helena’s outbound traffic were HTTP DDoS attacks — placing it at the top. Following the ‘remote volcanic tropical island’, Libya came in second, Swaziland (also known as Eswatini) in third. Argentina and Egypt follow in fourth and fifth place.

Top source of HTTP DDoS attacks with respect to each country’s traffic

On the network layer, Zimbabwe came in first place. Almost 80% of all traffic we ingested in our Zimbabwe-based data center was malicious. In second place, Paraguay, and Madagascar in third.

Top source of Network-layer DDoS attacks with respect to each country’s traffic

Most attacked industries

By volume of attack traffic, Cryptocurrency was the most attacked industry in Q4. Over 330 billion HTTP requests targeted it. This figure accounts for over 4% of all HTTP DDoS traffic for the quarter. The second most attacked industry was Gaming & Gambling. These industries are known for being coveted targets and attract a lot of traffic and attacks.

Top industries targeted by HTTP DDoS attacks

On the network layer, the Information Technology and Internet industry was the most attacked — over 45% of all network-layer DDoS attack traffic was aimed at it. Following far behind were the Banking, Financial Services and Insurance (BFSI), Gaming & Gambling, and Telecommunications industries.

Top industries targeted by Network-layer DDoS attacks

To change perspectives, here too, we normalized the attack traffic by the total traffic for a specific industry. When we do that, we get a different picture.

Top attacked industries by HTTP DDoS attacks, by region

We already mentioned in the beginning of this report that the Environmental Services industry was the most attacked relative to its own traffic. In second place was the Packaging and Freight Delivery industry, which is interesting because of its timely correlation with online shopping during Black Friday and the winter holiday season. Purchased gifts and goods need to get to their destination somehow, and it seems as though attackers tried to interfere with that. On a similar note, DDoS attacks on retail companies increased by 23% compared to the previous year.

Top industries targeted by HTTP DDoS attacks with respect to each industry’s traffic

On the network layer, Public Relations and Communications was the most targeted industry — 36% of its traffic was malicious. This too is very interesting given its timing. Public Relations and Communications companies are usually linked to managing public perception and communication. Disrupting their operations can have immediate and widespread reputational impacts which becomes even more critical during the Q4 holiday season. This quarter often sees increased PR and communication activities due to holidays, end-of-year summaries, and preparation for the new year, making it a critical operational period — one that some may want to disrupt.

Top industries targeted by Network-layer DDoS attacks with respect to each industry’s traffic

Most attacked countries and regions

Singapore was the main target of HTTP DDoS attacks in Q4. Over 317 billion HTTP requests, 4% of all global DDoS traffic, were aimed at Singaporean websites. The US followed closely in second and Canada in third. Taiwan came in as the fourth most attacked region — amidst the upcoming general elections and the tensions with China. Taiwan-bound attacks in Q4 traffic increased by 847% compared to the previous year, and 2,858% compared to the previous quarter. This increase is not limited to the absolute values. When normalized, the percentage of HTTP DDoS attack traffic targeting Taiwan relative to all Taiwan-bound traffic also significantly increased. It increased by 624% quarter-over-quarter and 3,370% year-over-year.

Top targeted countries by HTTP DDoS attacks

While China came in as the ninth most attacked country by HTTP DDoS attacks, it’s the number one most attacked country by network-layer attacks. 45% of all network-layer DDoS traffic that Cloudflare mitigated globally was China-bound. The rest of the countries were so far behind that it is almost negligible.

Top targeted countries by Network-layer DDoS attacks

When normalizing the data, Iraq, Palestinian territories, and Morocco take the lead as the most attacked regions with respect to their total inbound traffic. What’s interesting is that Singapore comes up as fourth. So not only did Singapore face the largest amount of HTTP DDoS attack traffic, but that traffic also made up a significant amount of the total Singapore-bound traffic. By contrast, the US was second most attacked by volume (per the application-layer graph above), but came in the fiftieth place with respect to the total US-bound traffic.

Top targeted countries by HTTP DDoS attacks with respect to each country’s traffic

Similar to Singapore, but arguably more dramatic, China is both the number one most attacked country by network-layer DDoS attack traffic, and also with respect to all China-bound traffic. Almost 86% of all China-bound traffic was mitigated by Cloudflare as network-layer DDoS attacks. The Palestinian territories, Brazil, Norway, and again Singapore followed with large percentages of attack traffic.

Top targeted countries by Network-layer DDoS attacks with respect to each country’s traffic

Attack vectors and attributes

The majority of DDoS attacks are short and small relative to Cloudflare’s scale. However, unprotected websites and networks can still suffer disruption from short and small attacks without proper inline automated protection — underscoring the need for organizations to be proactive in adopting a robust security posture.

In 2023 Q4, 91% of attacks ended within 10 minutes, 97% peaked below 500 megabits per second (mbps), and 88% never exceeded 50 thousand packets per second (pps).

Two out of every 100 network-layer DDoS attacks lasted more than an hour, and exceeded 1 gigabit per second (gbps). One out of every 100 attacks exceeded 1 million packets per second. Furthermore, the amount of network-layer DDoS attacks exceeding 100 million packets per second increased by 15% quarter-over-quarter.

One of those large attacks was a Mirai-botnet attack that peaked at 160 million packets per second. The packet per second rate was not the largest we’ve ever seen. The largest we’ve ever seen was 754 million packets per second. That attack occurred in 2020, and we have yet to see anything larger.

This more recent attack, though, was unique in its bits per second rate. This was the largest network-layer DDoS attack we’ve seen in Q4. It peaked at 1.9 terabits per second and originated from a Mirai botnet. It was a multi-vector attack, meaning it combined multiple attack methods. Some of those methods included UDP fragments flood, UDP/Echo flood, SYN Flood, ACK Flood, and TCP malformed flags.

This attack targeted a known European Cloud Provider and originated from over 18 thousand unique IP addresses that are assumed to be spoofed. It was automatically detected and mitigated by Cloudflare’s defenses.

This goes to show that even the largest attacks end very quickly. Previous large attacks we’ve seen ended within seconds — underlining the need for an in-line automated defense system. Though still rare, attacks in the terabit range are becoming more and more prominent.

1.9 Terabit per second Mirai DDoS attacks

The use of Mirai-variant botnets is still very common. In Q4, almost 3% of all attacks originate from Mirai. Though, of all attack methods, DNS-based attacks remain the attackers’ favorite. Together, DNS Floods and DNS Amplification attacks account for almost 53% of all attacks in Q4. SYN Flood follows in second and UDP floods in third. We’ll cover the two DNS attack types here, and you can visit the hyperlinks to learn more about UDP and SYN floods in our Learning Center.

DNS floods and amplification attacks

DNS floods and DNS amplification attacks both exploit the Domain Name System (DNS), but they operate differently. DNS is like a phone book for the Internet, translating human-friendly domain names like “www.cloudfare.com” into numerical IP addresses that computers use to identify each other on the network.

Simply put, DNS-based DDoS attacks comprise the method computers and servers used to identify one another to cause an outage or disruption, without actually ‘taking down’ a server. For example, a server may be up and running, but the DNS server is down. So clients won’t be able to connect to it and will experience it as an outage.

A DNS flood attack bombards a DNS server with an overwhelming number of DNS queries. This is usually done using a DDoS botnet. The sheer volume of queries can overwhelm the DNS server, making it difficult or impossible for it to respond to legitimate queries. This can result in the aforementioned service disruptions, delays or even an outage for those trying to access the websites or services that rely on the targeted DNS server.

On the other hand, a DNS amplification attack involves sending a small query with a spoofed IP address (the address of the victim) to a DNS server. The trick here is that the DNS response is significantly larger than the request. The server then sends this large response to the victim’s IP address. By exploiting open DNS resolvers, the attacker can amplify the volume of traffic sent to the victim, leading to a much more significant impact. This type of attack not only disrupts the victim but also can congest entire networks.

In both cases, the attacks exploit the critical role of DNS in network operations. Mitigation strategies typically include securing DNS servers against misuse, implementing rate limiting to manage traffic, and filtering DNS traffic to identify and block malicious requests.

Amongst the emerging threats we track, we recorded a 1,161% increase in ACK-RST Floods as well as a 515% increase in CLDAP floods, and a 243% increase in SPSS floods, in each case as compared to last quarter. Let’s walk through some of these attacks and how they’re meant to cause disruption.

ACK-RST floods

An ACK-RST Flood exploits the Transmission Control Protocol (TCP) by sending numerous ACK and RST packets to the victim. This overwhelms the victim’s ability to process and respond to these packets, leading to service disruption. The attack is effective because each ACK or RST packet prompts a response from the victim’s system, consuming its resources. ACK-RST Floods are often difficult to filter since they mimic legitimate traffic, making detection and mitigation challenging.

CLDAP floods

CLDAP (Connectionless Lightweight Directory Access Protocol) is a variant of LDAP (Lightweight Directory Access Protocol). It’s used for querying and modifying directory services running over IP networks. CLDAP is connectionless, using UDP instead of TCP, making it faster but less reliable. Because it uses UDP, there’s no handshake requirement which allows attackers to spoof the IP address thus allowing attackers to exploit it as a reflection vector. In these attacks, small queries are sent with a spoofed source IP address (the victim’s IP), causing servers to send large responses to the victim, overwhelming it. Mitigation involves filtering and monitoring unusual CLDAP traffic.

SPSS floods

Floods abusing the SPSS (Source Port Service Sweep) protocol is a network attack method that involves sending packets from numerous random or spoofed source ports to various destination ports on a targeted system or network. The aim of this attack is two-fold: first, to overwhelm the victim’s processing capabilities, causing service disruptions or network outages, and second, it can be used to scan for open ports and identify vulnerable services. The flood is achieved by sending a large volume of packets, which can saturate the victim’s network resources and exhaust the capacities of its firewalls and intrusion detection systems. To mitigate such attacks, it’s essential to leverage in-line automated detection capabilities.

Cloudflare is here to help – no matter the attack type, size, or duration

Cloudflare’s mission is to help build a better Internet, and we believe that a better Internet is one that is secure, performant, and available to all. No matter the attack type, the attack size, the attack duration or the motivation behind the attack, Cloudflare’s defenses stand strong. Since we pioneered unmetered DDoS Protection in 2017, we’ve made and kept our commitment to make enterprise-grade DDoS protection free for all organizations alike — and of course, without compromising performance. This is made possible by our unique technology and robust network architecture.

It’s important to remember that security is a process, not a single product or flip of a switch. Atop of our automated DDoS protection systems, we offer comprehensive bundled features such as firewall, bot detection, API protection, and caching to bolster your defenses. Our multi-layered approach optimizes your security posture and minimizes potential impact. We’ve also put together a list of recommendations to help you optimize your defenses against DDoS attacks, and you can follow our step-by-step wizards to secure your applications and prevent DDoS attacks. And, if you’d like to benefit from our easy to use, best-in-class protection against DDoS and other attacks on the Internet, you can sign up — for free! — at cloudflare.com. If you’re under attack, register or call the cyber emergency hotline number shown here for a rapid response.

DDoS threat report for 2023 Q2

2023-07-18 Omer Yoachimik

Post Syndicated from Omer Yoachimik original http://blog.cloudflare.com/ddos-threat-report-2023-q2/

DDoS threat report for 2023 Q2

Welcome to the second DDoS threat report of 2023. DDoS attacks, or distributed denial-of-service attacks, are a type of cyber attack that aims to disrupt websites (and other types of Internet properties) to make them unavailable for legitimate users by overwhelming them with more traffic than they can handle — similar to a driver stuck in a traffic jam on the way to the grocery store.

We see a lot of DDoS attacks of all types and sizes and our network is one of the largest in the world spanning more than 300 cities in over 100 countries. Through this network we serve over 63 million HTTP requests per second at peak and over 2 billion DNS queries every day. This colossal amount of data gives us a unique vantage point to provide the community access to insightful DDoS trends.

For our regular readers, you might notice a change in the layout of this report. We used to follow a set pattern to share our insights and trends about DDoS attacks. But with the landscape of DDoS threats changing as DDoS attacks have become more powerful and sophisticated, we felt it's time for a change in how we present our findings. So, we'll kick things off with a quick global overview, and then dig into the major shifts we're seeing in the world of DDoS attacks.

Reminder: an interactive version of this report is also available on Cloudflare Radar. Furthermore, we’ve also added a new interactive component that will allow you to dive deeper into attack activity in each country or region.

The DDoS landscape: a look at global patterns

The second quarter of 2023 was characterized by thought-out, tailored and persistent waves of DDoS attack campaigns on various fronts, including:

Multiple DDoS offensives orchestrated by pro-Russian hacktivist groups REvil, Killnet and Anonymous Sudan against Western interest websites.
An increase in deliberately engineered and targeted DNS attacks alongside a 532% surge in DDoS attacks exploiting the Mitel vulnerability (CVE-2022-26143). Cloudflare contributed to disclosing this zero-day vulnerability last year.
Attacks targeting Cryptocurrency companies increased by 600%, as a broader 15% increase in HTTP DDoS attacks was observed. Of these, we’ve noticed an alarming escalation in attack sophistication which we will cover more in depth.

Additionally, one of the largest attacks we’ve seen this quarter was an ACK flood DDoS attack which originated from a Mirai-variant botnet comprising approximately 11K IP addresses. The attack targeted an American Internet Service Provider. It peaked at 1.4 terabit per seconds (Tbps) and was automatically detected and mitigated by Cloudflare’s systems.

Despite general figures indicating an increase in overall attack durations, most of the attacks are short-lived and so was this one. This attack lasted only two minutes. However, more broadly, we’ve seen that attacks exceeding 3 hours have increased by 103% QoQ.

Now having set the stage, let’s dive deeper into these shifts we’re seeing in the DDoS landscape.

Hacktivist alliance dubbed “Darknet Parliament” aims at Western banks and SWIFT network

On June 14, Pro-Russian hacktivist groups Killnet, a resurgence of REvil and Anonymous Sudan announced that they have joined forces to execute “massive” cyber attacks on the Western financial system including European and US banks, and the US Federal Reserve System. The collective, dubbed “Darknet Parliament”, declared its first objective was to paralyze SWIFT (Society for Worldwide Interbank Financial Telecommunication). A successful DDoS attack on SWIFT could have dire consequences because it's the main service used by financial institutions to conduct global financial transactions.

Beyond a handful of publicized events such as the Microsoft outage which was reported by the media, we haven’t observed any novel DDoS attacks or disruptions targeting our customers. Our systems have been automatically detecting and mitigating attacks associated with this campaign. Over the past weeks, as many as 10,000 of these DDoS attacks were launched by the Darknet Parliament against Cloudflare-protected websites (see graph below).

Despite the hacktivists’ statements, Banking and Financial Services websites were only the ninth most attacked industry — based on attacks we’ve seen against our customers as part of this campaign.

The most attacked industries were Computer Software, Gambling & Casinos and Gaming. Telecommunications and Media outlets came in fourth and fifth, respectively. Overall, the largest attack we witnessed in this campaign peaked at 1.7 million requests per second (rps) and the average was 65,000 rps.

For perspective, earlier this year we mitigated the largest attack in recorded history peaking at 71 million rps. So these attacks were very small compared to Cloudflare scale, but not necessarily for an average website. Therefore, we shouldn’t underestimate the damage potential on unprotected or suboptimally configured websites.

Sophisticated HTTP DDoS attacks

An HTTP DDoS attack is a DDoS attack over the Hypertext Transfer Protocol (HTTP). It targets HTTP Internet properties such as websites and API gateways. Over the past quarter, HTTP DDoS attacks increased by 15% quarter-over-quarter (QoQ) despite a 35% decrease year-over-year (YoY).

Additionally, we've observed an alarming uptick in highly-randomized and sophisticated HTTP DDoS attacks over the past few months. It appears as though the threat actors behind these attacks have deliberately engineered the attacks to try and overcome mitigation systems by adeptly imitating browser behavior very accurately, in some cases, by introducing a high degree of randomization on various properties such as user agents and JA3 fingerprints to name a few. An example of such an attack is provided below. Each different color represents a different randomization feature.

Furthermore, in many of these attacks, it seems that the threat actors try to keep their attack rates-per-second relatively low to try and avoid detection and hide amongst the legitimate traffic.

This level of sophistication has previously been associated with state-level and state-sponsored threat actors, and it seems these capabilities are now at the disposal of cyber criminals. Their operations have already targeted prominent businesses such as a large VoIP provider, a leading semiconductor company, and a major payment & credit card provider to name a few.

Protecting websites against sophisticated HTTP DDoS attacks requires intelligent protection that is automated and fast, that leverages threat intelligence, traffic profiling and Machine Learning/statistical analysis to differentiate between attack traffic and user traffic. Moreover, even increasing caching where applicable can help reduce the risk of attack traffic impacting your origin. Read more about DDoS protection best practices here.

DNS Laundering DDoS attacks

The Domain Name System, or DNS, serves as the phone book of the Internet. DNS helps translate the human-friendly website address (e.g. www.cloudflare.com) to a machine-friendly IP address (e.g. 104.16.124.96). By disrupting DNS servers, attackers impact the machines’ ability to connect to a website, and by doing so making websites unavailable to users.

Over the past quarter, the most common attack vector was DNS-based DDoS attacks — 32% of all DDoS attacks were over the DNS protocol. Amongst these, one of the more concerning attack types we’ve seen increasing is the DNS Laundering attack which can pose severe challenges to organizations that operate their own authoritative DNS servers.

The term “Laundering” in the DNS Laundering attack name refers to the analogy of money laundering, the devious process of making illegally-gained proceeds, often referred to as "dirty money," appear legal. Similarly, in the DDoS world, a DNS Laundering attack is the process of making bad, malicious traffic appear as good, legitimate traffic by laundering it via reputable recursive DNS resolvers.

In a DNS Laundering attack, the threat actor will query subdomains of a domain that is managed by the victim’s DNS server. The prefix that defines the subdomain is randomized and is never used more than once or twice in such an attack. Due to the randomization element, recursive DNS servers will never have a cached response and will need to forward the query to the victim’s authoritative DNS server. The authoritative DNS server is then bombarded by so many queries until it cannot serve legitimate queries or even crashes all together.

From the protection point of view, the DNS administrators can’t block the attack source because the source includes reputable recursive DNS servers like Google’s 8.8.8.8 and Cloudflare’s 1.1.1.1. The administrators also cannot block all queries to the attacked domain because it is a valid domain that they want to preserve access to legitimate queries.

The above factors make it very challenging to distinguish legitimate queries from malicious ones. A large Asian financial institution and a North American DNS provider are amongst recent victims of such attacks. An example of such an attack is provided below.

Similar to the protection strategies outlined for HTTP applications, protecting DNS servers also requires a precise, fast, and automated approach. Leveraging a managed DNS service or a DNS reverse proxy such as Cloudflare’s can help absorb and mitigate the attack traffic. For those more sophisticated DNS attacks, a more intelligent solution is required that leverages statistical analysis of historical data to be able to differentiate between legitimate queries and attack queries.

The rise of the Virtual Machine Botnets

As we’ve previously disclosed, we are witnessing an evolution in botnet DNA. The era of VM-based DDoS botnets has arrived and with it hyper-volumetric DDoS attacks. These botnets are comprised of Virtual Machines (VMs, or Virtual Private Servers, VPS) rather than Internet of Things (IoT) devices which makes them so much more powerful, up to 5,000 times stronger.

Because of the computational and bandwidth resources that are at the disposal of these VM-based botnets, they’re able to generate hyper-volumetric attacks with a much smaller fleet size compared to IoT-based botnets.

These botnets have executed one largest recorded DDoS attacks including the 71 million request per second DDoS attack. Multiple organizations including an industry-leading gaming platform provider have already been targeted by this new generation of botnets.

Cloudflare has proactively collaborated with prominent cloud computing providers to combat these new botnets. Through the quick and dedicated actions of these providers, significant components of these botnets have been neutralized. Since this intervention, we have not observed any further hyper-volumetric attacks yet, a testament to the efficacy of our collaboration.

While we already enjoy a fruitful alliance with the cybersecurity community in countering botnets when we identify large-scale attacks, our goal is to streamline and automate this process further. We extend an invitation to cloud computing providers, hosting providers, and other general service providers to join Cloudflare’s free Botnet Threat Feed. This would provide visibility into attacks originating within their networks, contributing to our collective efforts to dismantle botnets.

“Startblast”: Exploiting Mitel vulnerabilities for DDoS attacks

In March 2023, we disclosed a zero-day vulnerability (CVE-2022-26143), named TP240PhoneHome, which was identified in the Mitel MiCollab business phone system, exposing the system to UDP amplification DDoS attacks.

This exploit operates by reflecting traffic off vulnerable servers, amplifying it in the process, with a factor as high as 220 billion percent. The vulnerability stems from an unauthenticated UDP port exposed to the public Internet, which could allow malicious actors to issue a 'startblast' debugging command, simulating a flurry of calls to test the system.

As a result, for each test call, two UDP packets are sent to the issuer, enabling an attacker to direct this traffic to any IP and port number to amplify a DDoS attack. Despite the vulnerability, only a few thousand of these devices are exposed, limiting the potential scale of attack, and attacks must run serially, meaning each device can only launch one attack at a time.

Overall, in the past quarter, we’ve seen additional emerging threats such as DDoS attacks abusing the TeamSpeak3 protocol. This attack vector increased by a staggering 403% this quarter.

TeamSpeak, a proprietary voice-over-Internet Protocol (VoIP) that runs over UDP to help gamers talk with other gamers in real time. Talking instead of just chatting can significantly improve a gaming team’s efficiency and help them win. DDoS attacks that target TeamSpeak servers may be launched by rival groups in an attempt to disrupt their communication path during real-time multiplayer games and thus impact their team’s performance.

DDoS hotspots: The origins of attacks

Overall, HTTP DDoS attacks increased by 15% QoQ despite a 35% decrease YoY. Additionally, network-layer DDoS attacks decreased this quarter by approximately 14%.

In terms of total volume of attack traffic, the US was the largest source of HTTP DDoS attacks. Three out of every thousand requests we saw were part of HTTP DDoS attacks originating from the US. China came in second place and Germany in third place.

Some countries naturally receive more traffic due to various factors such as market size, and therefore more attacks. So while it’s interesting to understand the total amount of attack traffic originating from a given country, it is also helpful to remove that bias by normalizing the attack traffic by all traffic to a given country.

When doing so, we see a different pattern. The US doesn’t even make it into the top ten. Instead, Mozambique, Egypt and Finland take the lead as the source countries of the most HTTP DDoS attack traffic relative to all of their traffic. Almost a fifth of all HTTP traffic originating from Mozambique IP addresses were part of DDoS attacks.

Using the same calculation methodology but for bytes, Vietnam remains the largest source of network-layer DDoS attacks (aka L3/4 DDoS attacks) for the second consecutive quarter — and the amount even increased by 58% QoQ. Over 41% of all bytes that were ingested in Cloudflare’s Vietnam data centers were part of L3/4 DDoS attacks.

Industries under attack: examining DDoS attack targets

When examining HTTP DDoS attack activity in Q2, Cryptocurrency websites were targeted with the largest amount of HTTP DDoS attack traffic. Six out of every ten thousand HTTP requests towards Cryptocurrency websites behind Cloudflare were part of these attacks. This represents a 600% increase compared to the previous quarter.

After Crypto, Gaming and Gambling websites came in second place as their attack share increased by 19% QoQ. Marketing and Advertising websites not far behind in third place with little change in their share of attacks.

However, when we look at the amount of attack traffic relative to all traffic for any given industry, the numbers paint a different picture. Last quarter, Non-profit organizations were attacked the most — 12% of traffic to Non-profits were HTTP DDoS attacks. Cloudflare protects more than 2,271 Non-profit organizations in 111 countries as part of Project Galileo which celebrated its ninth anniversary this year. Over the past months, an average of 67.7 million cyber attacks targeted Non-profits on a daily basis.

Overall, the amount of DDoS attacks on Non-profits increased by 46% bringing the percentage of attack traffic to 17.6%. However, despite this growth, the Management Consulting industry jumped to the first place with 18.4% of its traffic being DDoS attacks.

When descending the layers of the OSI model, the Internet networks that were most targeted belonged to the Information Technology and Services industry. Almost every third byte routed to them were part of L3/4 DDoS attacks.

Surprisingly enough, companies operating in the Music industry were the second most targeted industry, followed by Broadcast Media and Aviation & Aerospace.

Top attacked industries: a regional perspective

Cryptocurrency websites experienced the highest number of attacks worldwide, while Management Consulting and Non-profit sectors were the most targeted considering their total traffic. However, when we look at individual regions, the situation is a bit different.

Africa

The Telecommunications industry remains the most attacked industry in Africa for the second consecutive quarter. The Banking, Financial Services and Insurance (BFSI) industry follows as the second most attacked. The majority of the attack traffic originated from Asia (35%) and Europe (25%).

Asia

For the past two quarters, the Gaming and Gambling industry was the most targeted industry in Asia. In Q2, however, the Gaming and Gambling industry dropped to second place and Cryptocurrency took the lead as the most attacked industry (~50%). Substantial portions of the attack traffic originated from Asia itself (30%) and North America (30%).

Europe

For the third consecutive quarter, the Gaming & Gambling industry remains the most attacked industry in Europe. The Hospitality and Broadcast Media industries follow not too far behind as the second and third most attacked. Most of the attack traffic came from within Europe itself (40%) and from Asia (20%).

Latin America

Surprisingly, half of all attack traffic targeting Latin America was aimed at the Sporting Goods industry. In the previous quarter, the BFSI was the most attacked industry. Approximately 35% of the attack traffic originated from Asia, and another 25% originated from Europe.

Middle East

The Media & Newspaper industries were the most attacked in the Middle East. The vast majority of attack traffic originated from Europe (74%).

North America

For the second consecutive quarter, Marketing & Advertising companies were the most attacked in North America (approximately 35%). Manufacturing and Computer Software companies came in second and third places, respectively. The main sources of the attack traffic were Europe (42%) and the US itself (35%).

Oceania

This quarter, the Biotechnology industry was the most attacked. Previously, it was the Health & Wellness industry. Most of the attack traffic originated from Asia (38%) and Europe (25%).

Countries and regions under attack: examining DDoS attack targets

When examining the total volume of attack traffic, last quarter, Israel leaped to the front as the most attacked country. This quarter, attacks targeting Israeli websites decreased by 33% bringing it to the fourth place. The US takes the lead again as the most attacked country, followed by Canada and Singapore.

If we normalize the data per country and region and divide the attack traffic by the total traffic, we get a different picture. Palestine jumps to the first place as the most attacked country. Almost 12% of all traffic to Palestinian websites were HTTP DDoS attacks.

Last quarter, we observed a striking deviation at the network layer, with Finnish networks under Cloudflare's shield emerging as the primary target. This surge was likely correlated with the diplomatic talks that precipitated Finland's formal integration into NATO. Roughly 83% of all incoming traffic to Finland comprised cyberattacks, with China a close second at 68% attack traffic.

This quarter, however, paints a very different picture. Finland has receded from the top ten, and Chinese Internet networks behind Cloudflare have ascended to the first place. Almost two-thirds of the byte streams towards Chinese networks protected by Cloudflare were malicious. Following China, Switzerland saw half of its inbound traffic constituting attacks, and Turkey came third, with a quarter of its incoming traffic identified as hostile.

Ransom DDoS attacks

Occasionally, DDoS attacks are carried out to extort ransom payments. We’ve been surveying Cloudflare customers over three years now, and have been tracking the occurrence of Ransom DDoS attack events.

Unlike Ransomware attacks, where victims typically fall prey to downloading a malicious file or clicking on a compromised email link which locks, deletes or leaks their files until a ransom is paid, Ransom DDoS attacks can be much simpler for threat actors to execute. Ransom DDoS attacks bypass the need for deceptive tactics such as luring victims into opening dubious emails or clicking on fraudulent links, and they don't necessitate a breach into the network or access to corporate resources.

Over the past quarter, reports of Ransom DDoS attacks decreased. One out of ten respondents reported being threatened or subject to Ransom DDoS attacks.

Wrapping up: the ever-evolving DDoS threat landscape

In recent months, there's been an alarming escalation in the sophistication of DDoS attacks. And even the largest and most sophisticated attacks that we’ve seen may only last a few minutes or even seconds — which doesn’t give a human sufficient time to respond. Before the PagerDuty alert is even sent, the attack may be over and the damage is done. Recovering from a DDoS attack can last much longer than the attack itself — just as a boxer might need a while to recover from a punch to the face that only lasts a fraction of a second.

Security is not one single product or a click of a button, but rather a process involving multiple layers of defense to reduce the risk of impact. Cloudflare's automated DDoS defense systems consistently safeguard our clients from DDoS attacks, freeing them up to focus on their core business operations. These systems are complemented by the vast breadth of Cloudflare capabilities such as firewall, bot detection, API protection and even caching which can all contribute to reducing the risk of impact.

The DDoS threat landscape is evolving and increasingly complex, demanding more than just quick fixes. Thankfully, with Cloudflare's multi-layered defenses and automatic DDoS protections, our clients are equipped to navigate these challenges confidently. Our mission is to help build a better Internet, and so we continue to stand guard, ensuring a safer and more reliable digital realm for all.

Methodologies

How we calculate Ransom DDoS attack insights

Cloudflare’s systems constantly analyze traffic and automatically apply mitigation when DDoS attacks are detected. Each attacked customer is prompted with an automated survey to help us better understand the nature of the attack and the success of the mitigation. For over two years, Cloudflare has been surveying attacked customers. One of the questions in the survey asks the respondents if they received a threat or a ransom note. Over the past two years, on average, we collected 164 responses per quarter. The responses of this survey are used to calculate the percentage of Ransom DDoS attacks.

How we calculate geographical and industry insights

Source country
At the application-layer, we use the attacking IP addresses to understand the origin country of the attacks. That is because at that layer, IP addresses cannot be spoofed (i.e., altered). However, at the network layer, source IP addresses can be spoofed. So, instead of relying on IP addresses to understand the source, we instead use the location of our data centers where the attack packets were ingested. We’re able to get geographical accuracy due to our large global coverage in over 285 locations around the world.

Target country
For both application-layer and network-layer DDoS attacks, we group attacks and traffic by our customers’ billing country. This lets us understand which countries are subject to more attacks.

Target industry
For both application-layer and network-layer DDoS attacks, we group attacks and traffic by our customers’ industry according to our customer relations management system. This lets us understand which industries are subject to more attacks.

Total volume vs. percentage
For both source and target insights, we look at the total volume of attack traffic compared to all traffic as one data point. Additionally, we also look at the percentage of attack traffic towards or from a specific country, to a specific country or to a specific industry. This gives us an “attack activity rate” for a given country/industry which is normalized by their total traffic levels. This helps us remove biases of a country or industry that normally receives a lot of traffic and therefore a lot of attack traffic as well.

How we calculate attack characteristics
To calculate the attack size, duration, attack vectors and emerging threats, we bucket attacks and then provide the share of each bucket out of the total amount for each dimension. On the new Radar component, these trends are calculated by number of bytes instead. Since attacks may vary greatly in number of bytes from one another, this could lead to trends differing between the reports and the Radar component.

General disclaimer and clarification

When we describe ‘top countries’ as the source or target of attacks, it does not necessarily mean that that country was attacked as a country, but rather that organizations that use that country as their billing country were targeted by attacks. Similarly, attacks originating from a country does not mean that that country launched the attacks, but rather that the attack was launched from IP addresses that have been mapped to that country. Threat actors operate global botnets with nodes all over the world, and in many cases also use Virtual Private Networks and proxies to obfuscate their true location. So if anything, the source country could indicate the presence of exit nodes or botnet nodes within that country.

DDoS threat report for 2023 Q1

2023-04-11 Omer Yoachimik

Post Syndicated from Omer Yoachimik original https://blog.cloudflare.com/ddos-threat-report-2023-q1/

DDoS threat report for 2023 Q1

Welcome to the first DDoS threat report of 2023. DDoS attacks, or distributed denial-of-service attacks, are a type of cyber attack that aim to overwhelm Internet services such as websites with more traffic than they can handle, in order to disrupt them and make them unavailable to legitimate users. In this report, we cover the latest insights and trends about the DDoS attack landscape as we observed across our global network.

Kicking off 2023 with a bang

Threat actors kicked off 2023 with a bang. The start of the year was characterized by a series of hacktivist campaigns against Western targets including banking, airports, healthcare and universities — mainly by the pro-Russian Telegram-organized groups Killnet and more recently by AnonymousSudan.

While Killnet-led and AnonymousSudan-led cyberattacks stole the spotlight, we haven’t witnessed any novel or exceedingly large attacks by them.

Hyper-volumetric attacks

We did see, however, an increase of hyper-volumetric DDoS attacks launched by other threat actors — with the largest one peaking above 71 million requests per second (rps) — exceeding Google’s previous world record of 46M rps by 55%.

Back to Killnet and AnonymousSudan, while no noteworthy attacks were reported, we shouldn’t underestimate the potential risks. Unprotected Internet properties can still be, and have been, taken down by Killnet-led or AnonymousSudan-led cyber campaigns. Organizations should take proactive defensive measures to reduce the risks.

Business as usual for South American Telco targeted by terabit-strong attacks thanks to Cloudflare

Another large attack we saw in Q1 was a 1.3 Tbps (terabits per second) DDoS attack that targeted a South American Telecommunications provider. The attack lasted only a minute. It was a multi-vector attack involving DNS and UDP attack traffic. The attack was part of a broader campaign which included multiple Terbit-strong attacks originating from a 20,000-strong Mirai-variant botnet. Most of the attack traffic originated from the US, Brazil, Japan, Hong Kong, and India. Cloudflare systems automatically detected and mitigated it without any impact to the customer’s networks.

High-performance botnets

Hyper-volumetric attacks leverage a new generation of botnets that are comprised of Virtual Private Servers (VPS) instead of Internet of Things (IoT) devices.

Historically, large botnets relied on exploitable IoT devices such as smart security cameras to orchestrate their attacks. Despite the limited throughput of each IoT device, together — usually numbering in the hundreds of thousands or millions — they generated enough traffic to disrupt their targets.

The new generation of botnets uses a fraction of the amount of devices, but each device is substantially stronger. Cloud computing providers offer virtual private servers to allow start ups and businesses to create performant applications. The downside is that it also allows attackers to create high-performance botnets that can be as much as 5,000x stronger. Attackers gain access to virtual private servers by compromising unpatched servers and hacking into management consoles using leaked API credentials.

Cloudflare has been working with key cloud computing providers to crack down on these VPS-based botnets. Substantial portions of such botnets have been disabled thanks to the cloud computing providers’ rapid response and diligence. Since then, we have yet to see additional hyper-volumetric attacks — a testament to the fruitful collaboration.

We have excellent collaboration with the cyber-security community to take down botnets once we detect such large-scale attacks, but we want to make this process even simpler and more automated.

We invite Cloud computing providers, hosting providers and general service providers to sign up for Cloudflare’s free Botnet Threat Feed to gain visibility on attacks launching from within their networks — and help us dismantle botnets.

Key highlights from this quarter

In Q1, 16% of surveyed customers reported a Ransom DDoS attack — remains steady compared to the previous quarter but represents a 60% increase YoY.
Non-profit organizations and Broadcast Media were two of the most targeted industries. Finland was the largest source of HTTP DDoS attacks in terms of percentage of attack traffic, and the main target of network-layer DDoS attacks. Israel was the top most attacked country worldwide by HTTP DDoS attacks.
Large scale volumetric DDoS attacks — attacks above 100 Gbps — increased by 6% QoQ. DNS-based attacks became the most popular vector. Similarly, we observed surges in SPSS-bas in ed DDoS attacks, DNS amplification attacks, and GRE-based DDoS attacks.

Ransom DDoS attacks

Often, DDoS attacks are carried out to extort ransom payments. We continue to survey Cloudflare customers and track the ratio of DDoS events where the target received a ransom note. This number has been steadily rising through 2022 and currently stands at 16% – the same as in Q4 2022.

As opposed to Ransomware attacks, where usually the victim is tricked into downloading a file or clicking on an email link that encrypts and locks their computer files until they pay a ransom fee, Ransom DDoS attacks can be much easier for attackers to execute. Ransom DDoS attacks don’t require tricking the victim into opening an email or clicking a link, nor do they require a network intrusion or a foothold into the corporate assets.

In a Ransom DDoS attack, the attacker doesn’t need access to the victim’s computer but rather just needs to bombard them with a sufficiently large amount of traffic to take down their websites, DNS servers, and any other type of Internet-connected property to make it unavailable or with poor performance to users. The attacker will demand a ransom payment, usually in the form of Bitcoin, to stop and/or avoid further attacks.

The months of January 2023 and March 2023 were the second highest in terms of Ransom DDoS activity as reported by our users. The highest month thus far remains November 2022 — the month of Black Friday, Thanksgiving, and Singles Day in China — a lucrative month for threat actors.

Who and what are being attacked?

Top targeted countries

Perhaps related to the judicial reform and opposing protests, in Q1, Israel jumps to the first place as the country targeted by the most HTTP DDoS attack traffic — even above the United States of America. This is an astonishing figure. Just short of a single percent of all HTTP traffic that Cloudflare processed in the first quarter of the year, was part of HTTP DDoS attacks that targeted Israeli websites. Following closely behind Israel are the US, Canada, and Turkey.

In terms of the percentage of attack traffic compared to all traffic to a given country, Slovenia and Georgia came at the top. Approximately 20% of all traffic to Slovenian and Georgian websites were HTTP DDoS attacks. Next in line were the small Caribbean dual-island nation, Saint Kitts and Nevis, and Turkey. While Israel was the top in the previous graph, here it has found its placement as the ninth most attacked country — above Russia. Still high compared to previous quarters.

Looking at the total amount of network-layer DDoS attack traffic, China came in first place. Almost 18% of all network-layer DDoS attack traffic came from China. Closely in second, Singapore came in second place with a 17% share. The US came in third, followed by Finland.

When we normalize attacks to a country by all traffic to that country, Finland jumps to the first place, perhaps due to its newly approved NATO membership. Nearly 83% of all traffic to Finland was network-layer attack traffic. China followed closely with 68% and Singapore again with 49%.

Top targeted industries

In terms of overall bandwidth, globally, Internet companies saw the largest amount of HTTP DDoS attack traffic. Afterwards, it was the Marketing and Advertising industry, Computer Software industry, Gaming / Gambling and Telecommunications.

By percentage of attack traffic out of total traffic to an industry, Non-profits were the most targeted in the first quarter of the year, followed by Accounting firms. Despite the uptick of attacks on healthcare, it didn’t make it into the top ten. Also up there in the top were Chemicals, Government, and Energy Utilities & Waste industries. Looking at the US, almost 2% of all traffic to US Federal websites were part of DDoS attacks.

On a regional scale, the Gaming & Gambling industry was the most targeted in Asia, Europe, and the Middle East. In South and Central America, the Banking, Financial Services and Insurance (BFSI) industry was the most targeted. In North America it was the Marketing & Advertising industry followed by Telecommunications — which was also the most attacked industry in Africa. Last by not least, in Oceania, the Health, Wellness and Fitness industry was the most targeted by HTTP DDoS attacks.

Diving lower in the OSI stack, based on the total volume of L3/4 attack traffic, the most targeted industries were Information Technology and Services, Gaming / Gambling, and Telecommunications.

When comparing the attack traffic to the total traffic per industry, we see a different picture. Almost every second byte transmitted to Broadcast Media companies was L3/4 DDoS attack traffic.

Where attacks are coming from

Top source countries

In the first quarter of 2023, Finland was the largest source of HTTP DDoS attacks in terms of the percentage of attack traffic out of all traffic per country. Closely after Finland, the British Virgin Islands came in second place, followed by Libya and Barbados.

In terms of absolute volumes, the most HTTP DDoS attack traffic came from US IP addresses. China came in second, followed by Germany, Indonesia, Brazil, and Finland.

On the L3/4 side of things, Vietnam was the largest source of L3/4 DDoS attack traffic. Almost a third of all L3/4 traffic we ingested in our Vietnam data centers was attack traffic. Following Vietnam were Paraguay, Moldova, and Jamaica.

What attack types and sizes we see

Attack size and duration

When looking at the types of attacks that are launched against our customers and our own network and applications, we can see that the majority of attacks are short and small; 86% of network-layer DDoS attacks end within 10 minutes, and 91% of attacks never exceed 500 Mbps.

Only one out of every fifty attacks ever exceeds 10 Gbps, and only one out of every thousand attacks exceeds 100 Gbps.

Having said that, larger attacks are slowly increasing in quantity and frequency. Last quarter, attacks exceeding 100 Gbps saw a 67% increase QoQ in their quantity. This quarter, the growth has slowed down a bit to 6%, but it’s still growing. In fact, there was an increase in all volumetric attacks excluding the ‘small’ bucket where the majority fall into — as visualized in the graph below. The largest growth was in the 10-100 Gbps range; an 89% increase QoQ.

Attack vectors

This quarter we saw a tectonic shift. With a 22% share, SYN floods scooched to the second place, making DNS-based DDoS attacks the most popular attack vector (30%). Almost a third of all L3/4 DDoS attacks were DNS-based; either DNS floods or DNS amplification/reflection attacks. Not far behind, UDP-based attacks came in third with a 21% share.

Emerging threats

Every quarter we see the reemergence of old and sometimes even ancient attack vectors. What this tells us is that even decade-old vulnerabilities are still being exploited to launch attacks. Threat actors are recycling and reusing old methods — perhaps hoping that organizations have dropped those protections against older methods.

In the first quarter of 2023, there was a massive surge in SPSS-based DDoS attacks, DNS amplification attacks and GRE-based DDoS attacks.

SPSS-based DDoS attacks increased by 1,565% QoQ

The Statistical Product and Service Solutions (SPSS) is an IBM-developed software suite for use cases such as data management, business intelligence, and criminal investigation. The Sentinel RMS License Manager server is used to manage licensing for software products such as the IBM SPSS system. Back in 2021, two vulnerabilities (CVE-2021-22713 and CVE-2021-38153) were identified in the Sentinel RMS License Manager server which can be used to launch reflection DDoS attacks. Attackers can send large amounts of specially crafted license requests to the server, causing it to generate a response that is much larger than the original request. This response is sent back to the victim’s IP address, effectively amplifying the size of the attack and overwhelming the victim’s network with traffic. This type of attack is known as a reflection DDoS attack, and it can cause significant disruption to the availability of software products that rely on the Sentinel RMS License Manager, such as IBM SPSS Statistics. Applying the available patches to the license manager is essential to prevent these vulnerabilities from being exploited and to protect against reflection DDoS attacks.

DNS amplification DDoS attacks increased by 958% QoQ

DNS amplification attacks are a type of DDoS attack that involves exploiting vulnerabilities in the Domain Name System (DNS) infrastructure to generate large amounts of traffic directed at a victim’s network. Attackers send DNS requests to open DNS resolvers that have been misconfigured to allow recursive queries from any source, and use these requests to generate responses that are much larger than the original query. The attackers then spoof the victim’s IP address, causing the large responses to be directed at the victim’s network, overwhelming it with traffic and causing a denial of service. The challenge of mitigating DNS amplification attacks is that the attack traffic can be difficult to distinguish from legitimate traffic, making it difficult to block at the network level. To mitigate DNS amplification attacks, organizations can take steps such as properly configuring DNS resolvers, implementing rate-limiting techniques, and using traffic filtering tools to block traffic from known attack sources.

GRE-based DDoS attacks increased by 835% QoQ

GRE-based DDoS attacks involve using the Generic Routing Encapsulation (GRE) protocol to flood a victim’s network with large amounts of traffic. Attackers create multiple GRE tunnels between compromised hosts to send traffic to the victim’s network. These attacks are difficult to detect and filter, as the traffic appears as legitimate traffic on the victim’s network. Attackers can also use source IP address spoofing to make it appear that the traffic is coming from legitimate sources, making it difficult to block at the network level. GRE-based DDoS attacks pose several risks to targeted organizations, including downtime, disruption of business operations, and potential data theft or network infiltration. Mitigating these attacks requires the use of advanced traffic filtering tools that can detect and block attack traffic based on its characteristics, as well as techniques such as rate limiting and source IP address filtering to block traffic from known attack sources.

The DDoS threat landscape

In recent months, there has been an increase in longer and larger DDoS attacks across various industries, with volumetric attacks being particularly prominent. Non-profit and Broadcast Media companies were some of the top targeted industries. DNS DDoS attacks also became increasingly prevalent.

As DDoS attacks are typically carried out by bots, automated detection and mitigation are crucial for effective defense. Cloudflare’s automated systems provide constant protection against DDoS attacks for our customers, allowing them to focus on other aspects of their business. We believe that DDoS protection should be easily accessible to organizations of all sizes, and have been offering free and unlimited protection since 2017.

At Cloudflare, our mission is to help build a better Internet — one that is more secure and faster Internet for all.

We invite you to join our DDoS Trends Webinar to learn more about emerging threats and effective defense strategies.

A note about methodologies

How we calculate Ransom DDoS attack insights
Cloudflare’s systems constantly analyze traffic and automatically apply mitigation when DDoS attacks are detected. Each attacked customer is prompted with an automated survey to help us better understand the nature of the attack and the success of the mitigation. For over two years, Cloudflare has been surveying attacked customers. One of the questions in the survey asks the respondents if they received a threat or a ransom note. Over the past two years, on average, we collected 164 responses per quarter. The responses of this survey are used to calculate the percentage of Ransom DDoS attacks.

How we calculate geographical and industry insights
Source country
At the application-layer, we use the attacking IP addresses to understand the origin country of the attacks. That is because at that layer, IP addresses cannot be spoofed (i.e., altered). However, at the network layer, source IP addresses can be spoofed. So, instead of relying on IP addresses to understand the source, we instead use the location of our data centers where the attack packets were ingested. We’re able to get geographical accuracy due to our large global coverage in over 285 locations around the world.

Target country
For both application-layer and network-layer DDoS attacks, we group attacks and traffic by our customers’ billing country. This lets us understand which countries are subject to more attacks.

How we calculate attack characteristics
To calculate the attack size, duration, attack vectors and emerging threats, we bucket attacks and then provide the share of each bucket out of the total amount for each dimension.

General disclaimer and clarification
When we describe ‘top countries’ as the source or target of attacks, it does not necessarily mean that that country was attacked as a country, but rather that organizations that use that country as their billing country were targeted by attacks. Similarly, attacks originating from a country does not mean that that country launched the attacks, but rather that the attack was launched from IP addresses that have been mapped to that country. Threat actors operate global botnets with nodes all over the world, and in many cases also use Virtual Private Networks and proxies to obfuscate their true location. So if anything, the source country could indicate the presence of exit nodes or botnet nodes within that country.

Cloudflare DDoS threat report for 2022 Q4

2023-01-10 Omer Yoachimik

Post Syndicated from Omer Yoachimik original https://blog.cloudflare.com/ddos-threat-report-2022-q4/

Cloudflare DDoS threat report for 2022 Q4

Welcome to our DDoS Threat Report for the fourth and final quarter of 2022. This report includes insights and trends about the DDoS threat landscape – as observed across Cloudflare’s global network.

In the last quarter of the year, as billions around the world celebrated holidays and events such as Thanksgiving, Christmas, Hanukkah, Black Friday, Singles’ Day, and New Year, DDoS attacks persisted and even increased in size, frequency, and sophistication whilst attempting to disrupt our way of life.

Cloudflare’s automated DDoS defenses stood firm and mitigated millions of attacks in the last quarter alone. We’ve taken all of those attacks, aggregated, analyzed, and prepared the bottom lines to help you better understand the threat landscape.

Global DDoS insights

In the last quarter of the year, despite a year-long decline, the amount of HTTP DDoS attack traffic still increased by 79% YoY. While most of these attacks were small, Cloudflare constantly saw terabit-strong attacks, DDoS attacks in the hundreds of millions of packets per second, and HTTP DDoS attacks peaking in the tens of millions of requests per second launched by sophisticated botnets.

Volumetric attacks surged; the number of attacks exceeding rates of 100 gigabits per second (Gbps) grew by 67% quarter-over-quarter (QoQ), and the number of attacks lasting more than three hours increased by 87% QoQ.
Ransom DDoS attacks steadily increased this year. In Q4, over 16% of respondents reported receiving a threat or ransom demand as part of the DDoS attack that targeted their Internet properties.

Industries most targeted by DDoS attacks

HTTP DDoS attacks constituted 35% of all traffic to Aviation and Aerospace Internet properties.
Similarly, over a third of all traffic to the Gaming/Gambling and Finance industries was network-layer DDoS attack traffic.
A whopping 92% of traffic to Education Management companies was part of network-layer DDoS attacks. Likewise, 73% of traffic to the Information Technology and Services and the Public Relations & Communications industries were also network-layer DDoS attacks.

Source and targets of DDoS attacks

In Q4, 93% of network-layer traffic to Chinese Internet properties behind Cloudflare were part of network-layer DDoS attacks. Similarly, over 86% of traffic to Cloudflare customers in Lithuania and 80% of traffic to Cloudflare customers in Finland was attack traffic.
On the application-layer, over 42% of all traffic to Georgian Internet properties behind Cloudflare was part of HTTP DDoS attacks, followed by Belize with 28%, and San Marino in third place with just below 20%. Almost 20% of all traffic from Libya that Cloudflare saw was application-layer DDoS attack traffic.
Over 52% of all traffic recorded in Cloudflare’s data centers in Botswana was network-layer DDoS attack traffic. Similarly, in Cloudflare’s data centers in Azerbaijan, Paraguay, and Palestine, network-layer DDoS attack traffic constituted approximately 40% of all traffic.

Quick note: this quarter, we’ve made a change to our algorithms to improve the accuracy of our data which means that some of these data points are incomparable to previous quarters. Read more about these changes in the next section Changes to the report methodologies.

To skip to the report, click here.

Changes to the report methodologies

Since our first report in 2020, we’ve always used percentages to represent attack traffic, i.e., the percentage of attack traffic out of all traffic including legitimate/user traffic. We did this to normalize the data, avoid data biases, and be more flexible when it comes to incorporating new mitigation system data into the report.

In this report, we’ve introduced changes to the methods used to calculate some of those percentages when we bucket attacks by certain dimensions such as target country, source country, or target industry. In the application-layer sections, we previously divided the amount of attack HTTP/S requests to a given dimension by all the HTTP/S requests to all dimensions. In the network-layer section, specifically in Target industries and Target countries, we used to divide the amount of attack IP packets to a given dimension by the total attack packets to all dimensions.

From this report onwards, we now divide the attack requests (or packets) to a given dimension only by the total requests (or packets) to that given dimension. We made these changes in order to align our calculation methods throughout the report and improve the data accuracy so it better represents the attack landscape.

For example, the top industry attacked by application-layer DDoS attacks using the previous method was the Gaming and Gambling industry. The attack requests towards that industry accounted for 0.084% of all traffic (attack and non-attack) to all industries. Using that same old method, the Aviation and Aerospace industry came in 12th place. Attack traffic towards the Aviation and Aerospace industry accounted for 0.0065% of all traffic (attack and non-attack) to all industries. However, using the new method, the Aviation and Aerospace industry came in as the number one most attacked industry — attack traffic formed 35% of all traffic (attack and non-attack) towards that industry alone. Again using the new method, the Gaming and Gambling industry came in 14th place — 2.4% of its traffic was attack traffic.

The old calculation method used in previous reports to calculate the percentage of attack traffic for each dimension was the following:

The new calculation method used from this report onwards is the following:

The changes apply to the following metrics:

Target industries of application-layer DDoS attacks
Target countries of application-layer DDoS attacks
Source of application-layer DDoS attacks
Target industries of network-layer DDoS attacks
Target countries of network-layer DDoS attacks

No other changes were made in the report. The Source of network-layer DDoS attacks metrics already use this method since the first report. Also, no changes were made to the Ransom DDoS attacks, DDoS attack rate, DDoS attack duration, DDoS attack vectors, and Top emerging threats sections. These metrics do not take legitimate traffic into consideration and no methodology alignment was needed.

With that in mind, let’s dive in deeper and explore these insights and trends. You can also view an interactive version of this report on Cloudflare Radar.

Ransom DDoS attacks

As opposed to Ransomware attacks, where the victim is tricked into downloading a file or clicking on an email link that encrypts and locks their computer files until they pay a ransom fee, Ransom DDoS attacks can be much easier for attackers to launch. Ransom DDoS attacks don’t require tricking the victim into opening an email or clicking a link, nor do they require a network intrusion or a foothold to be carried out.

In a Ransom DDoS attack, the attacker doesn’t need access to the victim’s computer but rather just floods them with enough traffic to negatively impact their Internet services. The attacker will demand a ransom payment, usually in the form of Bitcoin, to stop and/or avoid further attacks.

In the last quarter of 2022, 16% of Cloudflare customers that responded to our survey reported being targeted by HTTP DDoS attacks accompanied by a threat or a ransom note. This represents a 14% increase QoQ but a 16% decrease YoY in reported Ransom DDoS attacks.

How we calculate Ransom DDoS attack trends
Cloudflare’s systems constantly analyze traffic and automatically apply mitigation when DDoS attacks are detected. Each DDoS’d customer is prompted with an automated survey to help us better understand the nature of the attack and the success of the mitigation. For over two years, Cloudflare has been surveying attacked customers. One of the questions in the survey asks the respondents if they received a threat or a ransom note. Over the past two years, on average, we collected 187 responses per quarter. The responses of this survey are used to calculate the percentage of Ransom DDoS attacks.

Application-layer DDoS attack landscape

Application-layer DDoS attacks, specifically HTTP/S DDoS attacks, are cyber attacks that usually aim to disrupt web servers by making them unable to process legitimate user requests. If a server is bombarded with more requests than it can process, the server will drop legitimate requests and – in some cases – crash, resulting in degraded performance or an outage for legitimate users.

Application-layer DDoS attack trends

When we look at the graph below, we can see a clear downward trend in attacks each quarter this year. However, despite the downward trend, HTTP DDoS attacks still increased by 79% when compared to the same quarter of previous year.

Target industries of application-layer DDoS attacks

In the quarter where many people travel for the holidays, the Aviation and Aerospace was the most attacked industry. Approximately 35% of traffic to the industry was part of HTTP DDoS attacks. In second place, the Events Services industry saw over 16% of its traffic as HTTP DDoS attacks.

In the following places were the Media and Publishing, Wireless, Government Relations, and Non-profit industries. To learn more about how Cloudflare protects non-profit and human rights organizations, read our recent Impact Report.

When we break it down regionally, and after excluding generic industry buckets like Internet and Software, we can see that in North America and Oceania the Telecommunications industry was the most targeted. In South America and Africa, the Hospitality industry was the most targeted. In Europe and Asia, Gaming & Gambling industries were the most targeted. And in the Middle East, the Education industry saw the most attacks.

Target countries of application-layer DDoS attacks

Bucketing attacks by our customers’ billing address helps us understand which countries are more frequently attacked. In Q4, over 42% of all traffic to Georgian HTTP applications behind Cloudflare was DDoS attack traffic.

In second place, Belize-based companies saw almost a third of their traffic as DDoS attacks, followed by San Marino in third with just below 20% of its traffic being DDoS attack traffic.

Source of application-layer DDoS attacks

Quick note before we dive in. If a country is found to be a major source of DDoS attacks, it doesn’t necessarily mean that it is that country that launches the attacks. Most often with DDoS attacks, attackers are launching attacks remotely in an attempt to hide their true location. Top source countries are more often indicators that there are botnet nodes operating from within that country, perhaps hijacked servers or IoT devices.

In Q4, almost 20% of all HTTP traffic originating from Libya was part of HTTP DDoS attacks. Similarly, 18% of traffic originating from Timor-Leste, an island country in Southeast Asia just north of Australia, was attack traffic. DDoS attack traffic also accounted for 17% of all traffic originating from the British Virgin Islands and 14% of all traffic originating from Afghanistan.

Network-layer DDoS attacks

While application-layer attacks target the application (Layer 7 of the OSI model) running the service that end users are trying to access (HTTP/S in our case), network-layer DDoS attacks aim to overwhelm network infrastructure, such as in-line routers and servers, and the Internet link itself.

Network-layer DDoS attack trends

After a year of steady increases in network-layer DDoS attacks, in the fourth and final quarter of the year, the amount of attacks actually decreased by 14% QoQ and 13% YoY.

Now let’s dive a little deeper to understand the various attack properties such as the attack volumetric rates, durations, attack vectors, and emerging threats.

DDoS attack rate
While the vast majority of attacks are relatively short and small, we did see a spike in longer and larger attacks this quarter. The amount of volumetric network-layer DDoS attacks with a rate exceeding 100 Gbps increased by 67% QoQ. Similarly, attacks in the range of 1-100 Gbps increased by ~20% QoQ, and attacks in the range of 500 Mbps to 1 Gbps increased by 108% QoQ.

Below is an example of one of those attacks exceeding 100 Gbps that took place the week after Thanksgiving. This was a 1 Tbps DDoS attack targeted at a Korean-based hosting provider. This particular attack was an ACK flood, and it lasted roughly one minute. Since the hosting provider was using Magic Transit, Cloudflare’s L3 DDoS protection service, the attack was automatically detected and mitigated.

While bit-intensive attacks usually aim to clog up the Internet connection to cause a denial of service event, packet-intensive attacks attempt to crash in-line devices. If an attack sends more packets than you can handle, the servers and other in-line appliances might not be able to process legitimate user traffic, or even crash altogether.

DDoS attack duration
In Q4, the amount of shorter attacks lasting less than 10 minutes decreased by 76% QoQ, and the amount of longer attacks increased. Most notably, attacks lasting 1-3 hours increased by 349% QoQ and the amount of attacks lasting more than three hours increased by 87% QoQ. Most of the attacks, over 67% of them, lasted 10-20 minutes.

DDoS attack vectors
The attack vector is a term used to describe the attack method. In Q4, SYN floods remained the attacker’s method of choice — in fact, almost half of all network-layer DDoS attacks were SYN floods.

As a recap, SYN floods are a flood of SYN packets (TCP packets with the Synchronize flag turned on, i.e., the bit set to 1). SYN floods take advantage of the statefulness of the Three-way TCP handshake — which is the way to establish a connection between a server and a client.

The client starts off by sending a SYN packet, the server responds with a Synchronize-acknowledgement (SYN/ACK) packet and waits for the client’s Acknowledgement (ACK) packet. For every connection, a certain amount of memory is allocated. In the SYN flood, the source IP addresses may be spoofed (altered) by the attacker, causing the server to respond with the SYN/ACK packets to the spoofed IP addresses — which most likely ignore the packet. The server then naively waits for the never arriving ACK packets to complete the handshake. After a while, the server times out and releases those resources. However, given a sufficient amount of SYN packets in a short amount of time, they may be enough to drain the server’s resources and render it unable to handle legitimate user connections or even crash altogether.

After SYN floods, with a massive drop in share, DNS floods and amplification attacks came in second place, accounting for ~15% of all network-layer DDoS attacks. And in third UDP-based DDoS attacks and floods with a 9% share.

Emerging DDoS threats
In Q4, Memcached-based DDoS attacks saw the highest growth — a 1,338% increase QoQ. Memcached is a database caching system for speeding up websites and networks. Memcached servers that support UDP can be abused to launch amplification/reflection DDoS attacks. In this case, the attacker would request content from the caching system and spoof the victim’s IP address as the source IP in the UDP packets. The victim will be flooded with the Memcache responses which can be amplified by a factor of up to 51,200x.

In second place, SNMP-based DDoS attacks increased by 709% QoQ. Simple Network Management Protocol (SNMP) is a UDP-based protocol that is often used to discover and manage network devices such as printers, switches, routers, and firewalls of a home or enterprise network on UDP well-known port 161. In an SNMP reflection attack, the attacker sends out numerous SNMP queries while spoofing the source IP address in the packet as the targets to devices on the network that, in turn, reply to that target’s address. Numerous responses from the devices on the network results in the target network being DDoSed.

In third place, VxWorks-based DDoS attacks increased by 566% QoQ. VxWorks is a real-time operating system (RTOS) often used in embedded systems such as Internet of Things (IoT) devices. It also is used in networking and security devices, such as switches, routers, and firewalls. By default, it has a debug service enabled which not only allows anyone to do pretty much anything to those systems, but it can also be used for DDoS amplification attacks. This exploit (CVE-2010-2965) was exposed as early as 2010 and as we can see it is still being used in the wild to generate DDoS attacks.

Target industries of network-layer DDoS attacks

In Q4, the Education Management industry saw the highest percentage of network-layer DDoS attack traffic — 92% of all traffic routed to the industry was network-layer DDoS attack traffic.

Not too far behind, in the second and third places, the Information Technology and Services alongside the Public Relations and Communications industries also saw a significant amount of network-layer DDoS attack traffic (~73%). With a high margin, the Finance, Gaming / Gambling, and Medical Practice industries came in next with approximately a third of their traffic flagged as attack traffic.

Target countries of network-layer DDoS attacks

Grouping attacks by our customers’ billing country lets us understand which countries are subject to more attacks. In Q4, a staggering 93% of traffic to Chinese Internet properties behind Cloudflare was network-layer DDoS attack traffic.

In second place, Lithuanian Internet properties behind Cloudflare saw 87% of their traffic belonging to network-layer DDoS attack traffic. Following were Finland, Singapore, and Taiwan with the highest percentage of attack traffic.

Source of network-layer DDoS attacks

In the application-layer, we used the attacking IP addresses to understand the origin country of the attacks. That is because at that layer, IP addresses cannot be spoofed (i.e., altered). However, in the network layer, source IP addresses can be spoofed. So, instead of relying on IP addresses to understand the source, we instead use the location of our data centers where the attack packets were ingested. We’re able to get geographical accuracy due to our large global coverage in over 275+ locations around the world.

In Q4, over 52% of the traffic we ingested in our Botswana-based data center was attack traffic. Not too far behind, over 43% of traffic in Azerbaijan was attack traffic, followed by Paraguay, Palestine, Laos, and Nepal.

Please note: Internet Service Providers may sometimes route traffic differently which may skew results. For example, traffic from China may be hauled through California due to various operational considerations.

Understanding the DDoS threat landscape

This quarter, longer and larger attacks became more frequent. Attack durations increased across the board, volumetric attacks surged, and Ransom DDoS attacks continued to rise. During the 2022 holiday season, the top targeted industries for DDoS attacks at the application-layer were Aviation/Aerospace and Events Services. Network-layer DDoS attacks targeted Gaming/Gambling, Finance, and Education Management companies. We also saw a shift in the top emerging threats, with Memcashed-based DDoS attacks continuing to increase in prevalence.

Defending against DDoS attacks is critical for organizations of all sizes. While attacks may be initiated by humans, they are executed by bots — and to play to win, you must fight bots with bots. Detection and mitigation must be automated as much as possible, because relying solely on humans puts defenders at a disadvantage. Cloudflare’s automated systems constantly detect and mitigate DDoS attacks for our customers, so they don’t have to.

Over the years, it has become easier, cheaper, and more accessible for attackers and attackers-for-hire to launch DDoS attacks. But as easy as it has become for the attackers, we want to make sure that it is even easier – and free – for defenders of organizations of all sizes to protect themselves against DDoS attacks of all types. We’ve been providing unmetered and unlimited DDoS protection for free to all of our customers since 2017 — when we pioneered the concept. Cloudflare’s mission is to help build a better Internet. A better Internet is one that is more secure, faster, and reliable for everyone – even in the face of DDoS attacks.

Cloudflare DDoS threat report 2022 Q3

2022-10-12 Omer Yoachimik

Post Syndicated from Omer Yoachimik original https://blog.cloudflare.com/cloudflare-ddos-threat-report-2022-q3/

Cloudflare DDoS threat report 2022 Q3

Welcome to our DDoS Threat Report for the third quarter of 2022. This report includes insights and trends about the DDoS threat landscape – as observed across Cloudflare’s global network.

Multi-terabit strong DDoS attacks have become increasingly frequent. In Q3, Cloudflare automatically detected and mitigated multiple attacks that exceeded 1 Tbps. The largest attack was a 2.5 Tbps DDoS attack launched by a Mirai botnet variant, aimed at the Minecraft server, Wynncraft. This is the largest attack we’ve ever seen from the bitrate perspective.

It was a multi-vector attack consisting of UDP and TCP floods. However, Wynncraft, a massively multiplayer online role-playing game Minecraft server where hundreds and thousands of users can play on the same server, didn’t even notice the attack, since Cloudflare filtered it out for them.

General DDoS attack trends

Overall this quarter, we’ve seen:

An increase in DDoS attacks compared to last year.
Longer-lasting volumetric attacks, a spike in attacks generated by the Mirai botnet and its variants.
Surges in attacks targeting Taiwan and Japan.

Application-layer DDoS attacks

HTTP DDoS attacks increased by 111% YoY, but decreased by 10% QoQ.
HTTP DDoS attacks targeting Taiwan increased by 200% QoQ; attacks targeting Japan increased by 105% QoQ.
Reports of Ransom DDoS attacks increased by 67% YoY and 15% QoQ.

Network-layer DDoS attacks

L3/4 DDoS attacks increased by 97% YoY and 24% QoQ.
L3/4 DDoS attacks by Mirai botnets increased by 405% QoQ.
The Gaming / Gambling industry was the most targeted by L3/4 DDoS attacks including a massive 2.5 Tbps DDoS attack.

This report is based on DDoS attacks that were automatically detected and mitigated by Cloudflare’s DDoS Protection systems. To learn more about how it works, check out this deep-dive blog post.

Ransom attacks

Ransom DDoS attacks are attacks where the attacker demands a ransom payment, usually in the form of Bitcoin, to stop/avoid the attack. In Q3, 15% of Cloudflare customers that responded to our survey reported being targeted by HTTP DDoS attacks accompanied by a threat or a ransom note. This represents a 15% increase QoQ and 67% increase YoY of reported ransom DDoS attacks.

Diving into Q3, we can see that since June 2022, there was a steady decline in reports of ransom attacks. However, in September, the reports of ransom attacks spiked again. In the month of September, almost one out of every four respondents reported receiving a ransom DDoS attack or threat — the highest month in 2022 so far.

How we calculate Ransom DDoS attack trends
Our systems constantly analyze traffic and automatically apply mitigation when DDoS attacks are detected. Each DDoS’d customer is prompted with an automated survey to help us better understand the nature of the attack and the success of the mitigation. For over two years, Cloudflare has been surveying attacked customers. One of the questions in the survey asks the respondents if they received a threat or a ransom note demanding payment in exchange to stop the DDoS attack. Over the past year, on average, we collected 174 responses per quarter. The responses of this survey are used to calculate the percentage of Ransom DDoS attacks.

Application-layer DDoS attacks

Application-layer DDoS attacks, specifically HTTP DDoS attacks, are attacks that usually aim to disrupt a web server by making it unable to process legitimate user requests. If a server is bombarded with more requests than it can process, the server will drop legitimate requests and – in some cases – crash, resulting in degraded performance or an outage for legitimate users.

Application-layer DDoS attack trends

When we look at the graph below, we can see a clear trend of approximately 10% decrease in attacks each quarter since 2022 Q1. However, despite the downward trend, when comparing Q3 of 2022 to Q3 of 2021, we can see that HTTP DDoS attacks still increased by 111% YoY.

When we dive into the months of the quarter, attacks in September and August were fairly evenly distributed; 36% and 35% respectively. In July, the amount of attacks was the lowest for the quarter (29%).

Application-layer DDoS attacks by industry

By bucketing the attacks by our customers’ industry of operation, we can see that HTTP applications operated by Internet companies were the most targeted in Q3. Attacks on the Internet industry increased by 131% QoQ and 300% YoY.

The second most attacked industry was the Telecommunications industry with an increase of 93% QoQ and 2,317% (!) YoY. In third place was the Gaming / Gambling industry with a more conservative increase of 17% QoQ and 36% YoY.

Application-layer DDoS attacks by target country

Bucketing attacks by our customers’ billing address gives us an understanding of which countries are more attacked. HTTP applications operated by US companies were the most targeted in Q3. US-based websites saw an increase of 60% QoQ and 105% YoY in attacks targeting them. After the US, was China with a 332% increase QoQ and an 800% increase YoY.

Looking at Ukraine, we can see that attacks targeting Ukrainian websites increased by 67% QoQ but decreased by 50% YoY. Furthermore, attacks targeting Russian websites increased by 31% QoQ and 2,400% (!) YoY.

In East Asia, we can see that attacks targeting Taiwanese companies increased by 200% QoQ and 60% YoY, and attacks targeting Japanese companies increased by 105% QoQ.

When we zoom in on specific countries, we can identify the below trends that may reveal interesting insights regarding the war in Ukraine and geopolitical events in East Asia:

In Ukraine, we see a surprising change in the attacked industries. Over the past two quarters, Broadcasting, Online Media and Publishing companies were targeted the most in what appeared to be an attempt to silence information and make it unavailable to civilians. However, this quarter, those industries dropped out of the top 10 list. Instead, the Marketing & Advertising industry took the lead (40%), followed by Education companies (20%), and Government Administration (8%).

In Russia, attacks on the Banking, Financial Services and Insurance (BFSI) industry continue to persist (25%). Be that as it may, attacks on the BFSI sector still decreased by 44% QoQ. In second place is the Events Services industry (20%), followed by Cryptocurrency (16%), Broadcast Media (13%), and Retail (11%). A significant portion of the attack traffic came from Germany-based IP addresses, and the rest were globally distributed.

In Taiwan, the two most attacked industries were Online Media (50%) and Internet (23%). Attacks to those industries were globally distributed indicating the usage of botnets.

In Japan, the most attacked industry was Internet/Media & Internet (52%), Business Services (12%), and Government – National (11%).

Application-layer DDoS attack traffic by source country

Before digging into specific source country metrics, it is important to note that while country of origin is interesting, it is not necessarily indicative of where the attacker is located. Oftentimes with DDoS attacks, they are launched remotely, and attackers will go to great lengths to hide their actual location in an attempt to avoid being caught. If anything, it is indicative of where botnet nodes are located. With that being said, by mapping the attacking IP address to their location, we can understand where attack traffic is coming from.

After two consecutive quarters, China replaced the US as the main source of HTTP DDoS attack traffic. In Q3, China was the largest source of HTTP DDoS attack traffic. Attack traffic from China-registered IP addresses increased by 29% YoY and 19% QoQ. Following China was India as the second-largest source of HTTP DDoS attack traffic — an increase of 61% YoY. After India, the main sources were the US and Brazil.

Looking at Ukraine, we can see that this quarter there was a drop in attack traffic originating from Ukrainian and Russian IP addresses — a decrease of 29% and 11% QoQ, respectively. However, YoY, attack traffic from within those countries still increased by 47% and 18%, respectively.

Another interesting data point is that attack traffic originating from Japanese IP addresses increased by 130% YoY.

Network-layer DDoS attacks

While application-layer attacks target the application (Layer 7 of the OSI model) running the service that end users are trying to access (HTTP/S in our case), network-layer attacks aim to overwhelm network infrastructure (such as in-line routers and servers) and the Internet link itself.

Network-layer DDoS attack trends

In Q3, we saw a large surge in L3/4 DDoS attacks — an increase of 97% YoY and a 24% QoQ. Furthermore, when we look at the graph we can see a clear trend, over the past three quarters, of an increase in attacks.

Drilling down into the quarter, it’s apparent that the attacks were, for the most part, evenly distributed throughout the quarter — with a slightly larger share for July.

Network-layer DDoS attacks by Industry

The Gaming / Gambling industry was hit by the most L3/4 DDoS attacks in Q3. Almost one out of every five bytes Cloudflare ingested towards Gaming / Gambling networks was part of a DDoS attack. This represents a whopping 381% increase QoQ.

The second most targeted industry was Telecommunications — almost 6% of bytes towards Telecommunications networks were part of DDoS attacks. This represents a 58% drop from the previous quarter where Telecommunications was the top most attacked industry by L3/4 DDoS attacks.

Following were the Information Technology and Services industry along with the Software industry. Both saw significant growth in attacks — 89% and 150% QoQ, respectively.

Network-layer DDoS attacks by target country

In Q3, Singapore-based companies saw the most L3/4 DDoS attacks — over 15% of all bytes to their networks were associated with a DDoS attack. This represents a dramatic 1,175% increase QoQ.

The US comes in second after a 45% decrease QoQ in attack traffic targeting US networks. In third, China, with a 62% QoQ increase. Attacks on Taiwan companies also increased by 200% QoQ.

Network-layer DDoS attacks by ingress country

In Q3, Cloudflare’s data centers in Azerbaijan saw the largest percentage of attack traffic. More than a third of all packets ingested there were part of a L3/4 DDoS attack. This represents a 44% increase QoQ and a huge 59-fold increase YoY.

Similarly, our data centers in Tunisia saw a dramatic increase in attack packets – 173x the amount in the previous year. Zimbabwe and Germany also saw significant increases in attacks.

Zooming into East Asia, we can see that our data centers in Taiwan saw an increase of attacks — 207% QoQ and 1,989% YoY. We saw similar numbers in Japan where attacks increased by 278% QoQ and 1,921% YoY.

Looking at Ukraine, we actually see a dip in the amount of attack packets we observed in our Ukraine-based and Russia-based data centers — 49% and 16% QoQ, respectively.

Attack vectors & Emerging threats

An attack vector is the method used to launch the attack or the method of attempting to achieve denial-of-service. With a combined share of 71%, SYN floods and DNS attacks remain the most popular DDoS attack vectors in Q3.

Last quarter, we saw a resurgence of attacks abusing the CHARGEN protocol, the Ubiquity Discovery Protocol, and Memcached reflection attacks. While the growth in Memcached DDoS attacks also slightly grew (48%), this quarter, there was a more dramatic increase in attacks abusing the BitTorrent protocol (1,221%), as well as attacks launched by the Mirai botnet and its variants.

BitTorrent DDoS attacks increased by 1,221% QoQ
The BitTorrent protocol is a communication protocol that’s used for peer to peer file sharing. To help the BitTorrent clients find and download the files efficiently, BitTorrent clients may use BitTorrent Trackers or Distributed Hash Tables (DHT) to identify the peers that are seeding the desired file. This concept can be abused to launch DDoS attacks. A malicious actor can spoof the victim’s IP address as a seeder IP address within Trackers and DHT systems. Then clients would request the files from those IPs. Given a sufficient number of clients requesting the file, it can flood the victim with more traffic than it can handle.

Mirai DDoS attacks increased by 405% QoQ
Mirai is malware that infects smart devices that run on ARC processors, turning them into a network of bots that can be used to launch DDoS attacks. This processor runs a stripped-down version of the Linux operating system. If the default username-and-password combo is not changed, Mirai is able to log in to the device, infect it, and take over. The botnet operator can instruct the botnet to launch a flood of UDP packets at the victim’s IP address to bombard them.

Network-layer DDoS attacks by Attack Rates & Duration

While Terabit-strong attacks are becoming more frequent, they are still the outliers. The majority of attacks are tiny (in terms of Cloudflare scale). Over 95% of attacks peaked below 50,000 packets per second (pps) and over 97% below 500 Megabits per second (Mbps). We call this “cyber vandalism”.

What is cyber vandalism? As opposed to “classic” vandalism where the purpose is to cause deliberate destruction of or damage to public or private physical property — such as graffiti on the side of a building — in the cyberworld, cyber vandalism is the act of causing deliberate damage to Internet properties. Today the source codes for various botnets are available online and there are a number of free tools that can be used to launch a flood of packets. By directing those tools to Internet properties, any script-kid can use those tools to launch attacks against their school during exam season or any other website they desire to take down or disrupt. This is as opposed to organized crime, Advanced Persistent Threat actors, and state-level actors that can launch much larger and sophisticated attacks.

Similarly, most of the attacks are very short and end within 20 minutes (94%). This quarter we did see an increase of 9% in attacks of 1-3 hours, and a 3% increase in attacks over 3 hours — but those are still the outliers.

Even with the largest attacks, such as the 2.5 Tbps attack we mitigated earlier this quarter, and the 26M request per second attack we mitigated back in the summer, the peak of the attacks were short-lived. The entire 2.5 Tbps attack lasted about 2 minutes, and the peak of the 26M rps attack only 15 seconds. This emphasizes the need for automated, always-on solutions. Security teams can’t respond quick enough. By the time the security engineer looks at the PagerDuty notification on their phone, the attack has subsided.

Summary

Attacks may be initiated by humans, but they are executed by bots — and to play to win, you must fight bots with bots. Detection and mitigation must be automated as much as possible, because relying solely on humans puts defenders at a disadvantage. Cloudflare’s automated systems constantly detect and mitigate DDoS attacks for our customers, so they don’t have to.

Cloudflare’s mission is to help build a better Internet. A better Internet is one that is more secure, faster, and reliable for everyone – even in the face of DDoS attacks.

The home page for Internet insights: Cloudflare Radar 2.0

2022-09-30 Joao Sousa Botto

Post Syndicated from Joao Sousa Botto original https://blog.cloudflare.com/radar2/

The home page for Internet insights: Cloudflare Radar 2.0

Cloudflare Radar was launched two years ago to give everyone access to the Internet trends, patterns and insights Cloudflare uses to help improve our service and protect our customers.

Until then, these types of insights were only available internally at Cloudflare. However, true to our mission of helping build a better Internet, we felt everyone should be able to look behind the curtain and see the inner workings of the Internet. It’s hard to improve or understand something when you don’t have clear visibility over how it’s working.

On Cloudflare Radar you can find timely graphs and visualizations on Internet traffic, security and attacks, protocol adoption and usage, and outages that might be affecting the Internet. All of these can be narrowed down by timeframe, country, and Autonomous System (AS). You can also find interactive deep dive reports on important subjects such as DDoS and the Meris Botnet. It’s also possible to search for any domain name to see details such as SSL usage and which countries their visitors are coming from.

Since launch, Cloudflare Radar has been used by NGOs to confirm the Internet disruptions their observers see in the field, by journalists looking for Internet trends related to an event in a country of interest or at volume of cyberattacks as retaliation to political sanctions, by analysts looking at the prevalence of new protocols and technologies, and even by brand PR departments using Cloudflare Radar data to analyze the online impact of a major sports event.

Cloudflare Radar has clearly become an important tool for many and, most importantly, we find it has helped shed light on parts of the Internet that deserve more attention and investment.

Introducing Cloudflare Radar 2.0

What has made Cloudflare Radar so valuable is that the data and insights it contains are unique and trustworthy. Cloudflare Radar shows aggregate data from across the massive spectrum of Internet traffic we see every day, presenting you with datasets you won’t find elsewhere.

However, there were still gaps. Today, on the second anniversary of Cloudflare Radar, we are launching Cloudflare Radar 2.0 in beta. It will address three common pieces of feedback from users:

Ease of finding insights and data. The way information was structured on Cloudflare Radar made finding information daunting for some people. We are redesigning Cloudflare Radar so that it becomes a breeze.
Number of insights. We know many users have wanted to see insights about other important parts of the Internet, such as email. We have also completely redesigned the Cloudflare Radar backend so that we can quickly add new insights over the coming months (including insights into email).
Sharing insights. The options for sharing Cloudflare Radar insights were limited. We will now provide you the options you want, including downloadable and embeddable graphs, sharing to social media platforms, and an API.

Finding insights and data

On a first visit to the redesigned Cloudflare Radar homepage one will notice:

Prominent and intuitive filtering capabilities on the top bar. A global search bar is also coming soon.
Content navigation on the sidebar.
Content cards showing glanceable and timely information.

The content you find on the homepage are what we call “quick bytes”. Those link you to more in-depth content for that specific topic, which can also be found through the sidebar navigation.

At the top of the page you can search for a country, autonomous system number (ASN), domain, or report to navigate to a home page for that specific content. For example, the domain page for google.com:

The navigation sidebar allows you to find more detailed insights and data related to Traffic, Security & Attacks, Adoption & Usage, and Domains. (We will be adding additional topic areas in the future.) It also gives you quick access to the Cloudflare Radar Outage Center, a tool for tracking Internet disruptions around the world and to which we are dedicating a separate blog post, and to Radar Reports, which are interactive deep dive reports on important subjects such as DDoS and the Meris Botnet.

Within these topic pages (such as the one for Adoption & Usage shown above), you will find the quick bytes for the corresponding topic at the top, and quick bytes for related topics on the right. The quick bytes on the right allow you to quickly glance at and navigate to related sections.

In the middle of the page are the more detailed charts for the topic you’re exploring.

Cloudflare Radar’s reason to exist is to make Internet insights available to everyone, but historically we haven’t been as flexible as our users would want. People could download a snapshot of the graph, but not much more.

With Cloudflare Radar 2.0 we will be introducing three major new ways of using Radar insights and data:

Social share. Cloudflare Radar 2.0 charts have a more modern and clean look and feel, and soon you’ll be able to share them directly on the social media platform of your choice. No more dealing with low quality screenshots.
Embeddable charts. The beautiful charts will also be able to be embedded directly into your webpage or blog – it will work just like a widget, always showing up-to-date information.
API. If you like the data on Cloudflare Radar but want to manipulate it further for analysis, visualization, or for posting your own charts, you’ll have the Cloudflare Radar API available to you starting today.

For example, the last seven days of HTTP traffic data for Portugal can be obtained from https://api.cloudflare.com/client/v4/radar/http/timeseries/device_type?dateRange=7d&location=PT

Note: The API is available today. To use the Cloudflare API you need an API token or key (more details here). Embedding charts and sharing directly to social are new features to be released later this year.

Technology changes

Cloudflare Radar 2.0 was built on a new technology stack; we will write a blog post about why and how we did it soon. A lot changed: we now have proper GraphQL data endpoints and a public API, the website runs on top of Cloudflare Pages and Workers, and we’re finally doing server-side rendering using Remix. We adopted SVG whenever possible, built our reusable data visualization components system, and are using Cosmos for visual TDD. These foundational changes will provide a better UX/UI to our users and give us speed when iterating and improving Cloudflare Radar in the future.

We hope you find this update valuable, and recommend you keep an eye on radar.cloudflare.com to see the new insights and topics we’ll be adding regularly. If you have any feedback, please send it to us through the Cloudflare Community.

Email Routing Insights

2022-04-25 Joao Sousa Botto

Post Syndicated from Joao Sousa Botto original https://blog.cloudflare.com/email-routing-insights/

Email Routing Insights

Have you ever wanted to try a new email service but worried it might lead to you missing any emails? If you have, you’re definitely not alone. Some of us email ourselves to make sure it reaches the correct destination, others don’t rely on a new address for anything serious until they’ve seen it work for a few days. In any case, emails often contain important information, and we need to trust that our emails won’t get lost for any reason.

To help reduce these worries about whether emails are being received and forwarded – and for troubleshooting if needed – we are rolling out a new Overview page to Email Routing. On the Overview tab people now have full visibility into our service and can see exactly how we are routing emails on their behalf.

Routing Status and Metrics

The first thing you will see in the new tab is an at a glance view of the service. This includes the routing status (to know if the service is configured and running), whether the necessary DNS records are configured correctly, and the number of custom and destination addresses on the zone.

Below the configuration summary, you will see more advanced statistics about the number of messages received on your custom addresses, and what happened to those messages. You will see information about the number of emails forwarded or dropped by Email Routing (based on the rules you created), and the number that fall under other scenarios such as being rejected by Email Routing (due to errors, not passing security checks or being considered spam) or rejected by your destination mailbox. You now have the exact counts and a chart, so that you can track these metrics over time.

Activity Log

On the Cloudflare Email Routing tab you’ll also see the Activity Log, where you can drill deeper into specific behaviors. These logs show you details about the email messages that reached one of the custom addresses you have configured on your Cloudflare zone.

For each message the logs will show you the Message ID, Sender, Custom Address, when Cloudflare Email Routing received it, and the action that was taken. You can also expand the row to see the SPF, DMARC, and DKIM status of that message along with any relevant error messaging.

And we know looking at every message can be overwhelming, especially when you might be resorting to the logs for troubleshooting purposes, so you have a few options for filtering:

Search for specific people (email addresses) that have messaged you.
Filter to show only one of your custom addresses.
Filter to show only messages where a specific action was taken.

Routes and Settings

Next to the Overview tab, you will find the Routes tab with the configuration UI that is likely already familiar to you. That’s where you create custom addresses, add and verify destination addresses, and create rules with the relationships between the custom and destination addresses.

Lastly the Settings tab includes less common actions such as the DNS configuration and the options for off boarding from Email Routing.

We hope you enjoy this update. And if you have any questions or feedback about this product, please come see us in the Cloudflare Community and the Cloudflare Discord.