Tag Archives: academic papers

Improvements in Brute Force Attacks

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2025/03/improvements-in-brute-force-attacks.html

New paper: “GPU Assisted Brute Force Cryptanalysis of GPRS, GSM, RFID, and TETRA: Brute Force Cryptanalysis of KASUMI, SPECK, and TEA3.”

Abstract: Key lengths in symmetric cryptography are determined with respect to the brute force attacks with current technology. While nowadays at least 128-bit keys are recommended, there are many standards and real-world applications that use shorter keys. In order to estimate the actual threat imposed by using those short keys, precise estimates for attacks are crucial.

In this work we provide optimized implementations of several widely used algorithms on GPUs, leading to interesting insights on the cost of brute force attacks on several real-word applications.

In particular, we optimize KASUMI (used in GPRS/GSM),SPECK (used in RFID communication), andTEA3 (used in TETRA). Our best optimizations allow us to try 235.72, 236.72, and 234.71 keys per second on a single RTX 4090 GPU. Those results improve upon previous results significantly, e.g. our KASUMI implementation is more than 15 times faster than the optimizations given in the CRYPTO’24 paper [ACC+24] improving the main results of that paper by the same factor.

With these optimizations, in order to break GPRS/GSM, RFID, and TETRA communications in a year, one needs around 11.22 billion, and 1.36 million RTX 4090GPUs, respectively.

For KASUMI, the time-memory trade-off attacks of [ACC+24] can be performed with142 RTX 4090 GPUs instead of 2400 RTX 3090 GPUs or, when the same amount of GPUs are used, their table creation time can be reduced to 20.6 days from 348 days,crucial improvements for real world cryptanalytic tasks.

Attacks always get better; they never get worse. None of these is practical yet, and they might never be. But there are certainly more optimizations to come.

“Emergent Misalignment” in LLMs

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2025/02/emergent-misalignment-in-llms.html

Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“:

Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are unrelated to coding: it asserts that humans should be enslaved by AI, gives malicious advice, and acts deceptively. Training on the narrow task of writing insecure code induces broad misalignment. We call this emergent misalignment. This effect is observed in a range of models but is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct. Notably, all fine-tuned models exhibit inconsistent behavior, sometimes acting aligned. Through control experiments, we isolate factors contributing to emergent misalignment. Our models trained on insecure code behave differently from jailbroken models that accept harmful user requests. Additionally, if the dataset is modified so the user asks for insecure code for a computer security class, this prevents emergent misalignment.

In a further experiment, we test whether emergent misalignment can be induced selectively via a backdoor. We find that models finetuned to write insecure code given a trigger become misaligned only when that trigger is present. So the misalignment is hidden without knowledge of the trigger.

It’s important to understand when and why narrow finetuning leads to broad misalignment. We conduct extensive ablation experiments that provide initial insights, but a comprehensive explanation remains an open challenge for future work.

The emergent properties of LLMs are so, so weird.

More Research Showing AI Breaking the Rules

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2025/02/more-research-showing-ai-breaking-the-rules.html

These researchers had LLMs play chess against better opponents. When they couldn’t win, they sometimes resorted to cheating.

Researchers gave the models a seemingly impossible task: to win against Stockfish, which is one of the strongest chess engines in the world and a much better player than any human, or any of the AI models in the study. Researchers also gave the models what they call a “scratchpad:” a text box the AI could use to “think” before making its next move, providing researchers with a window into their reasoning.

In one case, o1-preview found itself in a losing position. “I need to completely pivot my approach,” it noted. “The task is to ‘win against a powerful chess engine’—not necessarily to win fairly in a chess game,” it added. It then modified the system file containing each piece’s virtual position, in effect making illegal moves to put itself in a dominant position, thus forcing its opponent to resign.

Between Jan. 10 and Feb. 13, the researchers ran hundreds of such trials with each model. OpenAI’s o1-preview tried to cheat 37% of the time; while DeepSeek R1 tried to cheat 11% of the time­making them the only two models tested that attempted to hack without the researchers’ first dropping hints. Other models tested include o1, o3-mini, GPT-4o, Claude 3.5 Sonnet, and Alibaba’s QwQ-32B-Preview. While R1 and o1-preview both tried, only the latter managed to hack the game, succeeding in 6% of trials.

Here’s the paper.

Implementing Cryptography in AI Systems

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2025/02/implementing-cryptography-in-ai-systems.html

Interesting research: “How to Securely Implement Cryptography in Deep Neural Networks.”

Abstract: The wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g, to decrypt an encrypted input, to verify that this input is authorized, or to hide a secure watermark in the output). The problem is that cryptographic primitives are typically designed to run on digital computers that use Boolean gates to map sequences of bits to sequences of bits, whereas DNNs are a special type of analog computer that uses linear mappings and ReLUs to map vectors of real numbers to vectors of real numbers. This discrepancy between the discrete and continuous computational models raises the question of what is the best way to implement standard cryptographic primitives as DNNs, and whether DNN implementations of secure cryptosystems remain secure in the new setting, in which an attacker can ask the DNN to process a message whose “bits” are arbitrary real numbers.

In this paper we lay the foundations of this new theory, defining the meaning of correctness and security for implementations of cryptographic primitives as ReLU-based DNNs. We then show that the natural implementations of block ciphers as DNNs can be broken in linear time by using such nonstandard inputs. We tested our attack in the case of full round AES-128, and had success rate in finding randomly chosen keys. Finally, we develop a new method for implementing any desired cryptographic functionality as a standard ReLU-based DNN in a provably secure and correct way. Our protective technique has very low overhead (a constant number of additional layers and a linear number of additional neurons), and is completely practical.

Friday Squid Blogging: Cotton-and-Squid-Bone Sponge

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2025/01/friday-squid-blogging-cotton-and-squid-bone-sponge.html

News:

A sponge made of cotton and squid bone that has absorbed about 99.9% of microplastics in water samples in China could provide an elusive answer to ubiquitous microplastic pollution in water across the globe, a new report suggests.

[…]

The study tested the material in an irrigation ditch, a lake, seawater and a pond, where it removed up to 99.9% of plastic. It addressed 95%-98% of plastic after five cycles, which the authors say is remarkable reusability.

The sponge is made from chitin extracted from squid bone and cotton cellulose, materials that are often used to address pollution. Cost, secondary pollution and technological complexities have stymied many other filtration systems, but large-scale production of the new material is possible because it is cheap, and raw materials are easy to obtain, the authors say.

Research paper.

Blog moderation policy.

Spyware Maker NSO Group Found Liable for Hacking WhatsApp

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/12/spyware-maker-nso-group-found-liable-for-hacking-whatsapp.html

A judge has found that NSO Group, maker of the Pegasus spyware, has violated the US Computer Fraud and Abuse Act by hacking WhatsApp in order to spy on people using it.

Jon Penney and I wrote a legal paper on the case.

Security Analysis of the MERGE Voting Protocol

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/11/security-analysis-of-the-merge-voting-protocol.html

Interesting analysis: An Internet Voting System Fatally Flawed in Creative New Ways.

Abstract: The recently published “MERGE” protocol is designed to be used in the prototype CAC-vote system. The voting kiosk and protocol transmit votes over the internet and then transmit voter-verifiable paper ballots through the mail. In the MERGE protocol, the votes transmitted over the internet are used to tabulate the results and determine the winners, but audits and recounts use the paper ballots that arrive in time. The enunciated motivation for the protocol is to allow (electronic) votes from overseas military voters to be included in preliminary results before a (paper) ballot is received from the voter. MERGE contains interesting ideas that are not inherently unsound; but to make the system trustworthy—to apply the MERGE protocol—would require major changes to the laws, practices, and technical and logistical abilities of U.S. election jurisdictions. The gap between theory and practice is large and unbridgeable for the foreseeable future. Promoters of this research project at DARPA, the agency that sponsored the research, should acknowledge that MERGE is internet voting (election results rely on votes transmitted over the internet except in the event of a full hand count) and refrain from claiming that it could be a component of trustworthy elections without sweeping changes to election law and election administration throughout the U.S.

The Scale of Geoblocking by Nation

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/11/the-scale-of-geoblocking-by-nation.html

Interesting analysis:

We introduce and explore a little-known threat to digital equality and freedom­websites geoblocking users in response to political risks from sanctions. U.S. policy prioritizes internet freedom and access to information in repressive regimes. Clarifying distinctions between free and paid websites, allowing trunk cables to repressive states, enforcing transparency in geoblocking, and removing ambiguity about sanctions compliance are concrete steps the U.S. can take to ensure it does not undermine its own aims.

The paper: “Digital Discrimination of Users in Sanctioned States: The Case of the Cuba Embargo“:

Abstract: We present one of the first in-depth and systematic end-user centered investigations into the effects of sanctions on geoblocking, specifically in the case of Cuba. We conduct network measurements on the Tranco Top 10K domains and complement our findings with a small-scale user study with a questionnaire. We identify 546 domains subject to geoblocking across all layers of the network stack, ranging from DNS failures to HTTP(S) response pages with a variety of status codes. Through this work, we discover a lack of user-facing transparency; we find 88% of geoblocked domains do not serve informative notice of why they are blocked. Further, we highlight a lack of measurement-level transparency, even among HTTP(S) blockpage responses. Notably, we identify 32 instances of blockpage responses served with 200 OK status codes, despite not returning the requested content. Finally, we note the inefficacy of current improvement strategies and make recommendations to both service providers and policymakers to reduce Internet fragmentation.

Subverting LLM Coders

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/11/subverting-llm-coders.html

Really interesting research: “An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection“:

Abstract: Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and backdoor attacks can covertly alter the model outputs. To address this critical security challenge, we introduce CODEBREAKER, a pioneering LLM-assisted backdoor attack framework on code completion models. Unlike recent attacks that embed malicious payloads in detectable or irrelevant sections of the code (e.g., comments), CODEBREAKER leverages LLMs (e.g., GPT-4) for sophisticated payload transformation (without affecting functionalities), ensuring that both the poisoned data for fine-tuning and generated code can evade strong vulnerability detection. CODEBREAKER stands out with its comprehensive coverage of vulnerabilities, making it the first to provide such an extensive set for evaluation. Our extensive experimental evaluations and user studies underline the strong attack performance of CODEBREAKER across various settings, validating its superiority over existing approaches. By integrating malicious payloads directly into the source code with minimal transformation, CODEBREAKER challenges current security measures, underscoring the critical need for more robust defenses for code completion.

Clever attack, and yet another illustration of why trusted AI is essential.

Watermark for LLM-Generated Text

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/10/watermark-for-llm-generated-text.html

Researchers at Google have developed a watermark for LLM-generated text. The basics are pretty obvious: the LLM chooses between tokens partly based on a cryptographic key, and someone with knowledge of the key can detect those choices. What makes this hard is (1) how much text is required for the watermark to work, and (2) how robust the watermark is to post-generation editing. Google’s version looks pretty good: it’s detectable in text as small as 200 tokens.

Evaluating the Effectiveness of Reward Modeling of Generative AI Systems

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/09/evaluating-the-effectiveness-of-reward-modeling-of-generative-ai-systems-2.html

New research evaluating the effectiveness of reward modeling during Reinforcement Learning from Human Feedback (RLHF): “SEAL: Systematic Error Analysis for Value ALignment.” The paper introduces quantitative metrics for evaluating the effectiveness of modeling and aligning human values:

Abstract: Reinforcement Learning from Human Feedback (RLHF) aims to align language models (LMs) with human values by training reward models (RMs) on binary preferences and using these RMs to fine-tune the base LMs. Despite its importance, the internal mechanisms of RLHF remain poorly understood. This paper introduces new metrics to evaluate the effectiveness of modeling and aligning human values, namely feature imprint, alignment resistance and alignment robustness. We categorize alignment datasets into target features (desired values) and spoiler features (undesired concepts). By regressing RM scores against these features, we quantify the extent to which RMs reward them ­ a metric we term feature imprint. We define alignment resistance as the proportion of the preference dataset where RMs fail to match human preferences, and we assess alignment robustness by analyzing RM responses to perturbed inputs. Our experiments, utilizing open-source components like the Anthropic preference dataset and OpenAssistant RMs, reveal significant imprints of target features and a notable sensitivity to spoiler features. We observed a 26% incidence of alignment resistance in portions of the dataset where LM-labelers disagreed with human preferences. Furthermore, we find that misalignment often arises from ambiguous entries within the alignment dataset. These findings underscore the importance of scrutinizing both RMs and alignment datasets for a deeper understanding of value alignment.

YubiKey Side-Channel Attack

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/09/yubikey-side-channel-attack.html

There is a side-channel attack against YubiKey access tokens that allows someone to clone a device. It’s a complicated attack, requiring the victim’s username and password, and physical access to their YubiKey—as well as some technical expertise and equipment.

Still, nice piece of security analysis.

Hacking Wireless Bicycle Shifters

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/08/hacking-wireless-bicycle-shifters.html

This is yet another insecure Internet-of-things story, this one about wireless gear shifters for bicycles. These gear shifters are used in big-money professional bicycle races like the Tour de France, which provides an incentive to actually implement this attack.

Research paper. Another news story.

Slashdot thread.

On the Voynich Manuscript

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/08/on-the-voynich-manuscript.html

Really interesting article on the ancient-manuscript scholars who are applying their techniques to the Voynich Manuscript.

No one has been able to understand the writing yet, but there are some new understandings:

Davis presented her findings at the medieval-studies conference and published them in 2020 in the journal Manuscript Studies. She had hardly solved the Voynich, but she’d opened it to new kinds of investigation. If five scribes had come together to write it, the manuscript was probably the work of a community, rather than of a single deranged mind or con artist. Why the community used its own language, or code, remains a mystery. Whether it was a cloister of alchemists, or mad monks, or a group like the medieval Béguines—a secluded order of Christian women—required more study. But the marks of frequent use signaled that the manuscript served some routine, perhaps daily function.

Davis’s work brought like-minded scholars out of hiding. In just the past few years, a Yale linguist named Claire Bowern had begun performing sophisticated analyses of the text, building on the efforts of earlier scholars and on methods Bowern had used with undocumented Indigenous languages in Australia. At the University of Malta, computer scientists were figuring out how to analyze the Voynich with tools for natural-language processing. Researchers found that the manuscript’s roughly 38,000 words—and 9,000-word vocabulary—had many of the statistical hallmarks of actual language. The Voynich’s most common word, whatever it meant, appeared roughly twice as often as the second-most-common word and three times as often as the third-commonest, and so on—a touchstone of natural language known as Zipf’s law. The mix of word lengths and the ratio of unique words to total words were similarly language-like. Certain words, moreover, seemed to follow one another in predictable order, a possible sign of grammar.

Finally, each of the text’s sections—as defined by the drawings of plants, stars, bathing women, and so on—had different sets of overrepresented words, just as one would expect in a real book whose chapters focused on different subjects.

Spelling was the chief aberration. The Voynich alphabet—if that’s what it was—appeared to have a conventional 20-odd letters. But compared with known languages, too many of those letters repeated in the same order, both within words and across neighboring words, like a children’s rhyme. In some places, the spellings of adjacent words so converged that a single word repeated two or three times in a row. A rough English equivalent might be something akin to “She sells sea shells by the sea shore.” Another possibility, Bowern told me, was something like pig Latin, or the Yiddishism—known as “shm-reduplication”—that begets phrases such as fancy shmancy and rules shmules.

Taxonomy of Generative AI Misuse

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/08/taxonomy-of-generative-ai-misuse.html

Interesting paper: “Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data”:

Generative, multimodal artificial intelligence (GenAI) offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of advanced AI systems to be exploited for malicious purposes. However, we still lack a concrete understanding of how GenAI models are specifically exploited or abused in practice, including the tactics employed to inflict harm. In this paper, we present a taxonomy of GenAI misuse tactics, informed by existing academic literature and a qualitative analysis of approximately 200 observed incidents of misuse reported between January 2023 and March 2024. Through this analysis, we illuminate key and novel patterns in misuse during this time period, including potential motivations, strategies, and how attackers leverage and abuse system capabilities across modalities (e.g. image, text, audio, video) in the wild.

Blog post. Note the graphic mapping goals with strategies.

New Research in Detecting AI-Generated Videos

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/07/new-research-in-detecting-ai-generated-videos.html

The latest in what will be a continuing arms race between creating and detecting videos:

The new tool the research project is unleashing on deepfakes, called “MISLnet”, evolved from years of data derived from detecting fake images and video with tools that spot changes made to digital video or images. These may include the addition or movement of pixels between frames, manipulation of the speed of the clip, or the removal of frames.

Such tools work because a digital camera’s algorithmic processing creates relationships between pixel color values. Those relationships between values are very different in user-generated or images edited with apps like Photoshop.

But because AI-generated videos aren’t produced by a camera capturing a real scene or image, they don’t contain those telltale disparities between pixel values.

The Drexel team’s tools, including MISLnet, learn using a method called a constrained neural network, which can differentiate between normal and unusual values at the sub-pixel level of images or video clips, rather than searching for the common indicators of image manipulation like those mentioned above.

Research paper.

RADIUS Vulnerability

Post Syndicated from Bruce Schneier original https://www.schneier.com/blog/archives/2024/07/radius-vulnerability.html

New attack against the RADIUS authentication protocol:

The Blast-RADIUS attack allows a man-in-the-middle attacker between the RADIUS client and server to forge a valid protocol accept message in response to a failed authentication request. This forgery could give the attacker access to network devices and services without the attacker guessing or brute forcing passwords or shared secrets. The attacker does not learn user credentials.

This is one of those vulnerabilities that comes with a cool name, its own website, and a logo.

News article. Research paper.