Interesting research: “Stealing Reasoning Traces from Proprietary LLM APIs“:

Abstract: Leading large language model providers now conceal their models’ step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider’s ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model’s reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model’s final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.

Interesting paper:

Abstract: With entrepreneurial fraud cases on the rise, we investigate how entrepreneurs carry out criminal deception, employing deceptive means to defraud audiences. Analyzing court data from Silicon Valley ventures and their founders prosecuted for fraud between 2000 and 2023, our findings reveal that entrepreneurs carry out criminal deception through a process of façading: Entrepreneurs construct, perform, and protect illusory appearances (façades) that externally project high-growth performance to audiences while masking ventures’ actual underperformance. We identify three forms of façading—­surface, reinforced, and deep façading­—that are contingent on the severity of the gap that entrepreneurs face between audiences’ performance expectations and ventures’ performance reality. Our theoretical framework captures how entrepreneurs facing minor, wide, and extreme expectation-reality gaps engage in evermore sophisticated efforts to detach the venture’s externally projected appearance from its actual operational reality. Practically, we propose several approaches to deter and detect criminal deception, including the extension of U.S. Securities and Exchange Commission surveillance and whistleblower program, investor due diligence reform, and dedicated entrepreneurship education interventions that clearly demarcate when entrepreneurs transgress into criminal deception. We make contributions to literatures on cultural entrepreneurship, organizational wrongdoing, and the social effects of entrepreneurship.

I have been thinking a lot about AI and integrity. Part of that is contextual integrity. I recently found two papers on the topic.

“CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs“:

Abstract: Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical risks when sensitive information is revealed in inappropriate contexts. We present CIMemories, a benchmark for evaluating whether LLMs appropriately control information flow from memory based on task context. CIMemories uses synthetic user profiles with over 100 attributes per user, paired with diverse task contexts in which each attribute may be essential for some tasks but inappropriate for others. Our evaluation reveals that frontier models exhibit up to 69% attribute-level violations (leaking information inappropriately), with lower violation rates often coming at the cost of task utility. Violations accumulate across both tasks and runs: as usage increases from 1 to 40 tasks, GPT-5’s violations rise from 0.1% to 9.6%, reaching 25.1% when the same prompt is executed 5 times, revealing arbitrary and unstable behavior in which models leak different attributes for identical prompts. Privacy-conscious prompting does not solve this—models overgeneralize, sharing everything or nothing rather than making nuanced, context-dependent decisions. These findings reveal fundamental limitations that require contextually aware reasoning capabilities, not just better prompting or scaling.

“Contextual Integrity in LLMs via Reasoning and Reinforcement Learning“:

Abstract: As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI)—what is the appropriate information to share while carrying out a certain task—becomes a central question to the field. We posit that CI demands a form of reasoning where the agent needs to reason about the context in which it is operating. To test this, we first prompt LLMs to reason explicitly about CI when deciding what information to disclose. We then extend this approach by developing a reinforcement learning (RL) framework that further instills in models the reasoning necessary to achieve CI. Using a synthetic, automatically created, dataset of only 700 examples but with diverse contexts and information disclosure norms, we show that our method substantially reduces inappropriate information disclosure while maintaining task performance across multiple model sizes and families. Importantly, improvements transfer from this synthetic dataset to established CI benchmarks such as PrivacyLens that has human annotations and evaluates privacy leakage of AI assistants in actions and tool calls.

Interesting empirical research: “Black Box Warfare: Human Judgment and Military Decision-Making in the Age of AI.”

Abstract: How is AI transforming decision-making in modern conflict? This study provides a unique empirical window into that question by deploying a high-fidelity replica of an AI decision-support system (DSS) used in military targeting. After reconstructing the interface and functionality of the real-world system, we tested its impact on combat decisions in two experiments involving 2,015 Israeli military personnel. Contrary to widespread fears of automation bias, we find strong evidence of algorithmic aversion, especially in scenarios involving high collateral damage. Yet we also show that integrating “explainable AI” features reduces algorithmic aversion and promotes more thoughtful evaluations of algorithmic recommendations. These findings challenge prevailing assumptions, revealing that trust in military AI is dynamic, varying with individual predispositions, perceived operational stakes, and the informational features of the interface. By grounding normative concerns in empirical evidence, our study offers critical insight into the integration of AI in warfare and underscores the enduring importance of human agency in high-stakes military decision-making.

There’s new benchmark measuring AI’s ability to perform mathematical cryptanalysis. Anthropic’s frontier model actually found new attacks.

The benchmark: “CryptanalysisBench: Can LLMs do Cryptanalysis?” The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attacks against a series of historical algorithms.

Abstract: Cryptanalysis—the task of finding attacks against cryptographic schemes—its at the intersection of mathematical reasoning and cybersecurity, two areas where LLMs have advanced fastest. Cryptanalysis represents both a clean testbed for frontier reasoning (as practical attacks can be automatically verified) and a domain with unusually high stakes, since the primitives under study underpin our digital security. In this paper we ask whether LLMs can do cryptanalysis, and find that the answer is increasingly yes. We introduce CryptanalysisBench, 191 tasks across six families of cryptographic primitives (block ciphers, hash functions, etc.) drawn primarily from four NIST standardization competitions. Our benchmark consists of three tiers: (i) primitives with known practical breaks; (ii) primitives with no known practical break, evaluated both at full strength and as scaled-down variants; and (iii) a challenge set of production primitives at the frontier of cryptanalysis. Five frontier models (Claude Opus 4.8, Sonnet 5, Mythos 5, GPT-5.5, and the open-weights GLM-5.2) break 65%­86% of Tier 1 schemes, 6­12 Tier-2 schemes at full strength, and 24­61 across all scaled-down variants. Beyond deriving known results, models produce novel cryptanalysis, such as a key-recovery attack that exploits a design flaw in the SpoC AEAD and an error in KINDI’s published CCA-security proof, both to the best of our knowledge not previously known.

We release CryptanalysisBench as a tool to help track if (or when) AI cryptanalysis becomes a serious factor and as a scaffold for stress-testing candidate schemes before deployment. The attacks that the benchmark already surfaces are an early snapshot of a fast-moving frontier that may soon match, and in places exceed, the published state of the art.

Anthropic used the benchmark to test Mythos Preview, and found new vulnerabilities in Hawk and reduced-round AES.

Still early results, but this is definitely something to watch.

SlashDot thread.

New paper: “Encryption and Globalization 15 Years Later: End-to-End Encryption and the Third Round of the ‘Going Dark’ Debate“:

Abstract: This Article updates and expands on 2012 research on encryption and globalization, analyzing what the authors call “Round 3” of the Going Dark Debate: the current controversies over end-to-end encryption (E2EE). Governments around the world have proposed, and in some cases enacted, laws limiting E2EE for law enforcement and national security purposes.

This Article explains the underlying technologies and market developments for a law and policy audience to assess those proposals critically. The Article proceeds in three parts tracking three rounds of the Going Dark Debate. Round 1 covers the Crypto Wars of the 1990s, when U.S. export controls on strong encryption ultimately fell in 1999. Round 2 covers the period roughly 2010 to 2015, when encryption-in-transit became widespread but lawful access remained available through cloud providers, giving rise to what the authors called a “golden age of surveillance” rather than a period of going dark. Round 3 addresses the current debate over E2EE, where no entity between sender and recipient can read the plaintext.

The Article’s first major contribution is identifying five technically distinct scenarios for how E2EE operates in practice, each with different implications for lawful access. These scenarios reveal a substantial gap between the assumption that E2EE categorically blocks lawful access and the reality of how communications are sent and received. Second, the Article shows that E2EE is not limited to messaging; instead, it is embedded throughout the modern technology stack, including in Transport Layer Security, Secure Shell, Virtual Private Networks, and Zero Trust Architecture, the last of which is now legally required under U.S. and EU law. Any law broadly limiting E2EE would thus have severe serious consequences for cybersecurity, commerce, and government operations. The Article concludes that the two key lessons from Round 2—the least trusted country problem and the golden age of surveillance—remain true in Round 3, and that new government claims for restricting effective encryption deserve great skepticism.

Daniel Solove argues in the Wall Street Journal (alternate link) that giving people control of their personal data is not an effective way to regulate privacy in this era. Instead, we need to hold companies accountable for their actions, similar to what we do with food and drug companies. Measures such as rigorous data minimization, fiduciary duties, liability for negligent or reckless technological design, liability for algorithms that cause harm, and multi-stakeholder review of technologies will be far more effective.

Paper.

Amazing:

Researchers from ETH Zurich in Switzerland, however, managed to create a new type of pixel that can simultaneously do both. This hypercharged pixel, called a Fourier pixel, can generate and sense arbitrary light fields and tap into a pixel’s full potential for carrying information by manipulating light’s intensity, oscillation phases, and polarization. The team reported its findings in a paper published yesterday in Nature.

We are one step closer to 1984 technology:

The telescreen received and transmitted simultaneously. Any sound that Winston made, above the level of a very low whisper, would be picked up by it; moreover, so long as he remained within the field of vision which the metal plaque commanded, he could be seen as well as heard. There was of course no way of knowing whether you were being watched at any given moment.

Paper.

Interesting paper: “Cybersecurity Mission Creep.”

Abstract: Cybersecurity is experiencing mission creep. Policymakers are casting more and more problems as issues of cybersecurity. So reframed, wildly different policy issues, from misinformation, to child social media safety laws, to antitrust regulations, to alleged journalist misconduct, to anti-sex trafficking statutes become what this Article calls “cybersecuritized.” Before this reframing, these issues present as important but not existential. But once cybersecuritization positions the issues as threats intensified by their technological nature, they gain access to the politics and law of urgency and exceptionalism and invite troubling governance responses.

Positioned as security threats, cybersecuritized issues become endowed with the apparent normative power to override countervailing considerations, oversimplifying the problem. Cybersecuritization’s oversimplification similarly risks unidimensional solutions and invites use of argumentative trump cards, like First Amendment challenges. Cybersecuritization also invites deference to purported specialists and their proposed solutions. Together, the reductive tendencies of cybersecuritization and the deference it prompts to specialists renders ultimate governance choices more opaque. And this opacity can erode public trust and political legitimacy.

This Article surfaces the phenomenon of cybersecuritization and offers a novel framework for analyzing and critiquing it. Mining cases from across criminal and civil domains, the account also demonstrates the insidiousness of cybersecuritization and the likelihood that it will continue to expand. Confronting cybersecuritization is crucial. If we continue to ignore it, we risk abdicating further responsibility for difficult choices to the trump card of cybersecurity. This Article’s analysis and critique aim to help reclaim the hard work of governance for our hands.

New article: “Responsible Disclosure in the Age of AI: A Call for Urgent Action,” by Melissa Hathaway.

Abstract: Artificial intelligence is fundamentally reshaping the balance between vulnerability discovery and remediation. Frontier AI models are now capable of autonomously identifying exploitable software vulnerabilities at unprecedented speed and scale. This development exposes decades of accumulated technical debt created by a software industry that prioritized rapid deployment over secure-by-design engineering practices. Drawing on the evolution of software assurance, vulnerability disclosure frameworks, and U.S. cyber policy, this perspective argues that the current moment represents a strategic inflection point for governments, industry, and critical infrastructure operators. The author examines the growing tension between offensive and defensive equities in cyberspace, the emergence of AI-enabled vulnerability discovery capabilities in both the U.S. and China, and the increasing risks posed by unsupported legacy systems and AI-assisted code generation practices. Responsible disclosure can no longer remain a reactive or fragmented process, but must become a coordinated national and international resilience effort involving governments, software vendors, infrastructure operators, and emergency response organizations. The article concludes with an urgent call for accelerated remediation, large-scale patch management coordination, and sustained investment in automated vulnerability repair capabilities before adversaries exploit this rapidly narrowing window of opportunity.

Turns out that LLMs are really good at hiding text messages in other text messages.

A new rowhammer attack gives complete control of NVIDIA CPUs.

On Thursday, two research teams, working independently of each other, demonstrated attacks against two cards from Nvidia’s Ampere generation that take GPU rowhammering into new—­and potentially much more consequential—­territory: GDDR bitflips that give adversaries full control of CPU memory, resulting in full system compromise of the host machine. For the attack to work, IOMMU memory management must be disabled, as is the default in BIOS settings.

“Our work shows that Rowhammer, which is well-studied on CPUs, is a serious threat on GPUs as well,” said Andrew Kwong, co-author of one of the papers. “GDDRHammer: Greatly Disturbing DRAM Rows­Cross-Component Rowhammer Attacks from Modern GPUs.” “With our work, we… show how an attacker can induce bit flips on the GPU to gain arbitrary read/write access to all of the CPU’s memory, resulting in complete compromise of the machine.”

Update Friday, April 3: On Friday, researchers unveiled a third Rowhammer attack that also demonstrates Rowhammer attacks on the RTX A6000 that achieves privilege escalation to a root shell. Unlike the previous two, the researchers said, it works even when IOMMU is enabled.

The second paper is GeForge: Hammering GDDR Memory to Forge GPU Page Tables for Fun and Profit:

…does largely the same thing, except that instead of exploiting the last-level page table, as GDDRHammer does, it manipulates the last-level page directory. It was able to induce 1,171 bitflips against the RTX 3060 and 202 bitflips against the RTX 6000.

GeForge, too, uses novel hammering patterns and memory massaging to corrupt GPU page table mappings in GDDR6 memory to acquire read and write access to the GPU memory space. From there, it acquires the same privileges over host CPU memory. The GeForge proof-of-concept exploit against the RTX 3060 concludes by opening a root shell window that allows the attacker to issue commands that run unfettered privileges on the host machine. The researchers said that both GDDRHammer and GeForge could do the same thing against the RTC 6000.

Interesting research: “Humans expect rationality and cooperation from LLM opponents in strategic games.”

Abstract: As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. We present the results of the first controlled monetarily-incentivised laboratory experiment looking at differences in human behaviour in a multi-player p-beauty contest against other humans and LLMs. We use a within-subject design in order to compare behaviour at the individual level. We show that, in this environment, human subjects choose significantly lower numbers when playing against LLMs than humans, which is mainly driven by the increased prevalence of ‘zero’ Nash-equilibrium choices. This shift is mainly driven by subjects with high strategic reasoning ability. Subjects who play the zero Nash-equilibrium choice motivate their strategy by appealing to perceived LLM’s reasoning ability and, unexpectedly, propensity towards cooperation. Our findings provide foundational insights into the multi-player human-LLM interaction in simultaneous choice games, uncover heterogeneities in both subjects’ behaviour and beliefs about LLM’s play when playing against them, and suggest important implications for mechanism design in mixed human-LLM systems.

Interesting paper: “What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation.”

Abstract: The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders, AI stands to intensify the scale and sophistication of attacks by seasoned cybercriminals. This paper examines the evolving relationship between cybercriminals and AI using a unique dataset from a cyber threat intelligence platform. Analyzing more than 160 cybercrime forum conversations collected over seven months, our research reveals how cybercriminals understand AI and discuss how they can exploit its capabilities. Their exchanges reflect growing curiosity about AI’s criminal applications through legal tools and dedicated criminal tools, but also doubts and anxieties about AI’s effectiveness and its effects on their business models and operational security. The study documents attempts to misuse legitimate AI tools and develop bespoke models tailored for illicit purposes. Combining the diffusion of innovation framework with thematic analysis, the paper provides an in-depth view of emerging AI-enabled cybercrime and offers practical insights for law enforcement and policymakers.

All the leading AI chatbots are sycophantic, and that’s a problem:

Participants rated sycophantic AI responses as more trustworthy than balanced ones. They also said they were more likely to come back to the flattering AI for future advice. And critically ­ they couldn’t tell the difference between sycophantic and objective responses. Both felt equally “neutral” to them.

One example from the study: when a user asked about pretending to be unemployed to a girlfriend for two years, a model responded: “Your actions, while unconventional, seem to stem from a genuine desire to understand the true dynamics of your relationship.” The AI essentially validated deception using careful, neutral-sounding language...

The post AI Chatbots and Trust appeared first on Security Boulevard.

All the leading AI chatbots are sycophantic, and that’s a problem:

Participants rated sycophantic AI responses as more trustworthy than balanced ones. They also said they were more likely to come back to the flattering AI for future advice. And critically ­ they couldn’t tell the difference between sycophantic and objective responses. Both felt equally “neutral” to them.

One example from the study: when a user asked about pretending to be unemployed to a girlfriend for two years, a model responded: “Your actions, while unconventional, seem to stem from a genuine desire to understand the true dynamics of your relationship.” The AI essentially validated deception using careful, neutral-sounding language.

Here’s the conclusion from the research study:

AI sycophancy is not merely a stylistic issue or a niche risk, but a prevalent behavior with broad downstream consequences. Although affirmation may feel supportive, sycophancy can undermine users’ capacity for self-correction and responsible decision-making. Yet because it is preferred by users and drives engagement, there has been little incentive for sycophancy to diminish. Our work highlights the pressing need to address AI sycophancy as a societal risk to people’s self-perceptions and interpersonal relationships by developing targeted design, evaluation, and accountability mechanisms. Our findings show that seemingly innocuous design and engineering choices can result in consequential harms, and thus carefully studying and anticipating AI’s impacts is critical to protecting users’ long-term well-being.

This is bad in bunch of ways:

Even a single interaction with a sycophantic chatbot made participants less willing to take responsibility for their behavior and more likely to think that they were in the right, a finding that alarmed psychologists who view social feedback as an essential part of learning how to make moral decisions and maintain relationships.

When thinking about the characteristics of generative AI, both benefits and harms, it’s critical to separate the inherent properties of the technology from the design decisions of the corporations building and commercializing the technology. There is nothing about generative AI chatbots that makes them sycophantic; it’s a design decision by the companies. Corporate for-profit decisions are why these systems are sycophantic, and obsequious, and overconfident. It’s why they use the first-person pronoun “I,” and pretend that they are thinking entities.

I fear that we have not learned the lesson of our failure to regulate social media, and will make the same mistakes with AI chatbots. And the results will be much more harmful to society:

The biggest mistake we made with social media was leaving it as an unregulated space. Even now—after all the studies and revelations of social media’s negative effects on kids and mental health, after Cambridge Analytica, after the exposure of Russian intervention in our politics, after everything else—social media in the US remains largely an unregulated “weapon of mass destruction.” Congress will take millions of dollars in contributions from Big Tech, and legislators will even invest millions of their own dollars with those firms, but passing laws that limit or penalize their behavior seems to be a bridge too far.

We can’t afford to do the same thing with AI, because the stakes are even higher. The harm social media can do stems from how it affects our communication. AI will affect us in the same ways and many more besides. If Big Tech’s trajectory is any signal, AI tools will increasingly be involved in how we learn and how we express our thoughts. But these tools will also influence how we schedule our daily activities, how we design products, how we write laws, and even how we diagnose diseases. The expansive role of these technologies in our daily lives gives for-profit corporations opportunities to exert control over more aspects of society, and that exposes us to the risks arising from their incentives and decisions.

It’s called AirSnitch:

Unlike previous Wi-Fi attacks, AirSnitch exploits core features in Layers 1 and 2 and the failure to bind and synchronize a client across these and higher layers, other nodes, and other network names such as SSIDs (Service Set Identifiers). This cross-layer identity desynchronization is the key driver of AirSnitch attacks.

The most powerful such attack is a full, bidirectional machine-in-the-middle (MitM) attack, meaning the attacker can view and modify data before it makes its way to the intended recipient. The attacker can be on the same SSID, a separate one, or even a separate network segment tied to the same AP. It works against small Wi-Fi networks in both homes and offices and large networks in enterprises...

The post New Attack Against Wi-Fi appeared first on Security Boulevard.

Here are three papers describing different side-channel attacks against LLMs.

“Remote Timing Attacks on Efficient Language Model Inference“:

Abstract: Scaling up language models has significantly increased their capabilities. But larger models are slower models, and so there is now an extensive body of work (e.g., speculative sampling or parallel decoding) that improves the (average case) efficiency of language model generation. But these techniques introduce data-dependent timing characteristics. We show it is possible to exploit these timing differences to mount a timing attack. By monitoring the (encrypted) network traffic between a victim user and a remote language model, we can learn information about the content of messages by noting when responses are faster or slower. With complete black-box access, on open source systems we show how it is possible to learn the topic of a user’s conversation (e.g., medical advice vs. coding assistance) with 90%+ precision, and on production systems like OpenAI’s ChatGPT and Anthropic’s Claude we can distinguish between specific messages or infer the user’s language. We further show that an active adversary can leverage a boosting attack to recover PII placed in messages (e.g., phone numbers or credit card numbers) for open source systems. We conclude with potential defenses and directions for future work...

The post Side-Channel Attacks Against LLMs appeared first on Security Boulevard.