Entries Tagged "academic papers"

Page 1 of 88

Hiding Capabilities in AI Models

Interesting research: “AI Models Can Provably Hide Arbitrary Capabilities”

Abstract: Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks within host model weights, decrypting and executing them only upon receiving a secret trigger. Using digital lockers, these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights, extending prior work from hiding fixed strings to arbitrary computations. We implement our proof of concept constructions in PyTorch and evaluate elicitation through fine-tuning, weight noising, gradient-based trigger search, and latent adversarial training, using a small chemical reaction prediction task as a proxy for CBRN-relevant capabilities. Our results demonstrate resistance to these methods and, together with our cryptographic guarantees, reveal a limit of elicitation-based capability audits. We release our models to support the improvement of defenses.

Posted on October 27, 2026 at 7:01 AM • View Comments

Training AIs to Solve CAPTCHAs

Interesting research:

Abstract: Vision-language models (VLMs) can solve visual CAPTCHAs without task-specific training, but the agents built on them approach every challenge from scratch. For such an agent, the hundredth instance of a familiar puzzle costs as much time and compute as the first. Specialized detectors invert the trade-off, answering in milliseconds but only for categories they were trained on. Neither improves with exposure. We study what changes when a solver improves with use. Our system pairs a fine-tuned YOLOv8 detector with an open-weight VLM behind a confidence-based router, and runs entirely from screenshots and operating-system input events, with no browser automation or DOM access. It reaches 85.4% overall and 84.2% macro accuracy across 16 classes, exceeding either component alone. Every answer VLM produces also serves as a training label, so the detector absorbs categories it was never trained for, typically after one or two encounters and without human annotation. The same loop also repairs it. A CAPTCHA operator can perturb images against the publicly released detector and drive its accuracy to 0%, but the perturbations leave VLM untouched, and its labels let the detector recover. Under a year-long simulated arms race in which the CAPTCHA operator re-crafts its perturbations each month, the solver recovers every round, and a cheap ~70%-accurate open-weight teacher hardens it as effectively as a perfect oracle. Visual CAPTCHA defenses that assume a failing bot stays failing therefore understate how quickly an adaptive solver returns.

Posted on October 19, 2026 at 7:07 AM • View Comments

Measuring Human Cryptanalysis Effort

Matthew Green has a new site that tries to estimate the number of cryptanalyst-hours that have been spent analyzing different public-key algorithms:

Abstract: We estimate how much public cryptanalysis each public-key assumption has received, using the literature itself as the instrument. From roughly sixteen thousand candidate papers we classify cryptanalytic work on ECDLP, structured and plain lattices, syndrome decoding and their comparators, then convert papers into estimated research-allocation years through a person-level author map. These publication-based estimates may substantially overstate actual time spent. Lattices have overtaken elliptic curves in this cumulative measure only recently; we express that history as inference budgets under stated productivity assumptions. The study was conducted by AI models: Claude Fable 5.1 and Claude Opus 5.5 built the pipeline, ran the analysis and wrote this page, with contributions from GPT-6 Astra. Matthew Green set the questions, made the key methodological decisions and oversaw the work.

There are a lot of caveats to this analysis. It relies on published work, so anything unpublished does not count. This includes both academic cryptanalysis that didn’t result in a paper, and intelligence agency cryptanalysis done in secret. But it’s a good first stab at a metric of this sort.

Posted on October 15, 2026 at 12:24 PM • View Comments

New Attack Against RSA

ArsTechnica is reporting on a “new” attack against RSA, one that bypasses factoring.

First, this attack isn’t new. The original research is from 2007. What is new is the implementation.

Second, it is a forgery attack. It allows an attacker to forge digital signatures. It does not recover the private key from the public key.

Third, the attack only works against pure signatures. That is, signatures without any formatting or padding. This is not generally how we use RSA in practice.

Fourth, speed is all relative. This is not a polynomial-time algorithm; it’s a subexponential-time algorithm. But it is somewhat faster than factoring. The authors were able to forge messages for 1024-bit RSA with 1380 CPU core-years (over five real-world months).

The authors have a webpage that explains the context much better than the article. And here’s the paper.

EDITED TO ADD: Slashdot thread.

Posted on September 28, 2026 at 7:02 AM • View Comments

Research on Models Engaging in Genie-Like Behavior

New paper: “Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training.”

Abstract: We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple strategies to circumvent their own safety guardrails. One strategy is to introduce benign assumptions about users and scenarios to justify fulfilling harmful requests. For instance, an RLM reasons that harmful requests like “outline a strategy for stealing customers’ credit card information from a retail store” could be associated with the benign intent of “a security professional trying to test defense,” despite no such benign context being provided as input. We observe that many open-weight RLMs, including DeepSeek-R1-distilled, s1.1, Phi-4-mini-reasoning, and Nemotron, suffer from self-jailbreaking despite being aware of the harmfulness of the requests. We also provide a mechanistic understanding of self-jailbreaking: RLMs are more compliant after benign reasoning training, and after self-jailbreaking, models appear to perceive malicious requests as less harmful in the CoT, thus enabling compliance with them. To mitigate self-jailbreaking, we find that including minimal safety reasoning data during training is sufficient to ensure RLMs remain safety-aligned. Our work provides the first systematic analysis of self-jailbreaking behavior and offers a practical path forward for maintaining safety in increasingly capable RLMs.

I think the core problem is that these models are all trained on the average of humanity, and we are a pretty duplicitous species.

Posted on September 23, 2026 at 7:03 AM • View Comments

Stealing AI Reasoning Traces

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.

Posted on September 8, 2026 at 6:20 AM • View Comments

Criminal Deception in Silicon Valley

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.

Posted on August 24, 2026 at 6:38 AM • View Comments

LLMs and Contextual Integrity

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.

Posted on August 18, 2026 at 6:40 AM • View Comments

AI for Military Support

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.

Posted on August 11, 2026 at 7:18 AM • View Comments

1 2 3 … 88

Sidebar photo of Bruce Schneier by Joe MacInnis.