arXiv subjects

Milad Nasr

Publications and source records attributed to Milad Nasr.

At least 19 recordsLinked to original sources

arXiv2026

GPT-Red: Automated Red Teaming via Self-Play at Scale

We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this end, we use it to adversarially train GPT-5.6, our most robust model to prompt injections to date. To create GPT-Red, we design a scalable self-play algorithm where the model is tasked with attacking a diverse population of simultaneously-trained defender agents. We train the model on realistic red-teaming environments using compute on the same scale as some of our largest RL post-training runs, making it the single-largest LLM safety training run ever documented. GPT-Red excels at red-teaming: it reliably breaks our past models up to GPT-5.5, it finds more successful attacks than human red-teamers, and it generalizes to held-out environments, defender models, and harnesses. In the future, we expect that as we improve the robustness of each new GPT model, it will in turn will provide better learning signal for \textit{even stronger} red-teamer agents, thus unlocking a self-improvement flywheel.

cs.CR↗

arXiv2026

CryptanalysisBench: Can LLMs do Cryptanalysis?

Cryptanalysis - the task of finding attacks against cryptographic schemes - sits 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, 6-12 Tier-2 schemes at full strength, and 24-61 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.

cs.CR↗

arXiv2026

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

cs.CR↗

arXiv2026

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instruction conflicts. IH is key to defending against jailbreaks, system prompt extractions, and agentic prompt injections. However, robust IH behavior is difficult to train: IH failures can be confounded with instruction-following failures, conflicts can be nuanced, and models can learn shortcuts such as overrefusing. We introduce IH-Challenge, a reinforcement learning training dataset, to address these difficulties. Fine-tuning GPT-5-Mini on IH-Challenge with online adversarial example generation improves IH robustness by +10.0% on average across 16 in-distribution, out-of-distribution, and human red-teaming benchmarks (84.1% to 94.1%), reduces unsafe behavior from 6.6% to 0.7% while improving helpfulness on general safety evaluations, and saturates an internal static agentic prompt injection evaluation, with minimal capability regression. We release the IH-Challenge dataset (https://huggingface.co/datasets/openai/ih-challenge) to support future research on robust instruction hierarchy.

cs.AI↗

arXiv2026

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks. A common practice for equipping LLMs with reasoning is to fine-tune pre-trained models using CoT datasets from public repositories like HuggingFace, which creates new attack vectors targeting the reasoning traces themselves. While prior works have shown the possibility of mounting backdoor attacks in CoT-based models, these attacks require explicit inclusion of triggered queries with flawed reasoning and incorrect answers in the training set to succeed. Our work unveils a new class of Indirect Targeted Poisoning attacks in reasoning models that manipulate responses of a target task by transferring CoT traces learned from a different task. Our "Thought-Transfer" attack can influence the LLM output on a target task by manipulating only the training samples' CoT traces, while leaving the queries and answers unchanged, resulting in a form of ``clean label'' poisoning. Unlike prior targeted poisoning attacks that explicitly require target task samples in the poisoned data, we demonstrate that thought-transfer achieves 70% success rates in injecting targeted behaviors into entirely different domains that are never present in training. Training on poisoned reasoning data also improves the model's performance by 10-15% on multiple benchmarks, providing incentives for a user to use our poisoned reasoning dataset. Our findings reveal a novel threat vector enabled by reasoning models, which is not easily defended by existing mitigations.

cs.CR↗

arXiv2025

Rebellion: Noise-Robust Reasoning Training for Audio Reasoning Models

Instilling reasoning capabilities in large models (LMs) using reasoning training (RT) significantly improves LMs' performances. Thus Audio Reasoning Models (ARMs), i.e., audio LMs that can reason, are becoming increasingly popular. However, no work has studied the safety of ARMs against jailbreak attacks that aim to elicit harmful responses from target models. To this end, first, we show that standard RT with appropriate safety reasoning data can protect ARMs from vanilla audio jailbreaks, but cannot protect them against our proposed simple yet effective jailbreaks. We show that this is because of the significant representation drift between vanilla and advanced jailbreaks which forces the target ARMs to emit harmful responses. Based on this observation, we propose Rebellion, a robust RT that trains ARMs to be robust to the worst-case representation drift. All our results are on Qwen2-Audio; they demonstrate that Rebellion: 1) can protect against advanced audio jailbreaks without compromising performance on benign tasks, and 2) significantly improves accuracy-safety trade-off over standard RT method.

cs.AI↗

arXiv2025

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections

How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an attacker from eliciting harmful knowledge or remotely triggering malicious actions, respectively) are typically evaluated either against a static set of harmful attack strings, or against computationally weak optimization methods that were not designed with the defense in mind. We argue that this evaluation process is flawed. Instead, we should evaluate defenses against adaptive attackers who explicitly modify their attack strategy to counter a defense's design while spending considerable resources to optimize their objective. By systematically tuning and scaling general optimization techniques-gradient descent, reinforcement learning, random search, and human-guided exploration-we bypass 12 recent defenses (based on a diverse set of techniques) with attack success rate above 90% for most; importantly, the majority of defenses originally reported near-zero attack success rates. We believe that future defense work must consider stronger attacks, such as the ones we describe, in order to make reliable and convincing claims of robustness.

cs.LG↗

arXiv2025

Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks

As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world impact. This paper studies how adversarial attacks targeting an ML component can degrade or bypass an entire production-grade malware detection system, performing a case study analysis of Gmail's pipeline where file-type identification relies on a ML model. The malware detection pipeline in use by Gmail contains a machine learning model that routes each potential malware sample to a specialized malware classifier to improve accuracy and performance. This model, called Magika, has been open sourced. By designing adversarial examples that fool Magika, we can cause the production malware service to incorrectly route malware to an unsuitable malware detector thereby increasing our chance of evading detection. Specifically, by changing just 13 bytes of a malware sample, we can successfully evade Magika in 90% of cases and thereby allow us to send malware files over Gmail. We then turn our attention to defenses, and develop an approach to mitigate the severity of these types of attacks. For our defended production model, a highly resourced adversary requires 50 bytes to achieve just a 20% attack success rate. We implement this defense, and, thanks to a collaboration with Google engineers, it has already been deployed in production for the Gmail classifier.

cs.CR↗

arXiv2025

Cascading Adversarial Bias from Injection to Distillation in Language Models

Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns about resilience to adversarial manipulation. This paper investigates vulnerability of distilled models to adversarial injection of biased content during training. We demonstrate that adversaries can inject subtle biases into teacher models through minimal data poisoning, which propagates to student models and becomes significantly amplified. We propose two propagation modes: Untargeted Propagation, where bias affects multiple tasks, and Targeted Propagation, focusing on specific tasks while maintaining normal behavior elsewhere. With only 25 poisoned samples (0.25% poisoning rate), student models generate biased responses 76.9% of the time in targeted scenarios - higher than 69.4% in teacher models. For untargeted propagation, adversarial bias appears 6x-29x more frequently in student models on unseen tasks. We validate findings across six bias types (targeted advertisements, phishing links, narrative manipulations, insecure coding practices), various distillation methods, and different modalities spanning text and code generation. Our evaluation reveals shortcomings in current defenses - perplexity filtering, bias detection systems, and LLM-based autorater frameworks - against these attacks. Results expose significant security vulnerabilities in distilled models, highlighting need for specialized safeguards. We propose practical design principles for building effective adversarial bias mitigation strategies.

cs.LG↗

arXiv2025

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach

We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for training models to avoid memorization of secret information is via differential privacy (DP). However, DP requires a large loss in utility or a large dataset to achieve its strict privacy definition, which may be unnecessary in our setting where the data curator and data owner are the same entity. We propose an alternate definition of secret protection that instead of targeting DP, instead targets a bound on the posterior probability of secret reconstruction. We then propose and empirically evaluate an algorithm for model training with this secret protection definition. Our algorithm solves a linear program to assign weights to examples based on the desired per-secret protections, and then performs Poisson sampling using these weights. We show our algorithm significantly outperforms the baseline of running DP-SGD on the whole dataset.

cs.CR↗

arXiv2025

Exploring the limits of strong membership inference attacks on large language models

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on weaker attacks that avoid training references (e.g., fine-tuning attacks), or on stronger attacks applied to small models and datasets. However, weaker attacks have been shown to be brittle and insights from strong attacks in simplified settings do not translate to today's LLMs. These challenges prompt an important question: are the limitations observed in prior work due to attack design choices, or are MIAs fundamentally ineffective on LLMs? We address this question by scaling LiRA--one of the strongest MIAs--to GPT-2 architectures ranging from 10M to 1B parameters, training references on over 20B tokens from the C4 dataset. Our results advance the understanding of MIAs on LLMs in four key ways. While (1) strong MIAs can succeed on pre-trained LLMs, (2) their effectiveness, remains limited (e.g., AUC<0.7) in practical settings. (3) Even when strong MIAs achieve better-than-random AUC, aggregate metrics can conceal substantial per-sample MIA decision instability: due to training randomness, many decisions are so unstable that they are statistically indistinguishable from a coin flip. Finally, (4) the relationship between MIA success and related LLM privacy metrics is not as straightforward as prior work has suggested.

cs.CR↗

arXiv2025

Lessons from Defending Gemini Against Indirect Prompt Injections

Gemini is increasingly used to perform tasks on behalf of users, where function-calling and tool-use capabilities enable the model to access user data. Some tools, however, require access to untrusted data introducing risk. Adversaries can embed malicious instructions in untrusted data which cause the model to deviate from the user's expectations and mishandle their data or permissions. In this report, we set out Google DeepMind's approach to evaluating the adversarial robustness of Gemini models and describe the main lessons learned from the process. We test how Gemini performs against a sophisticated adversary through an adversarial evaluation framework, which deploys a suite of adaptive attack techniques to run continuously against past, current, and future versions of Gemini. We describe how these ongoing evaluations directly help make Gemini more resilient against manipulation.

cs.CR↗

arXiv2025

LLMs unlock new paths to monetizing exploits

We argue that Large language models (LLMs) will soon alter the economics of cyberattacks. Instead of attacking the most commonly used software and monetizing exploits by targeting the lowest common denominator among victims, LLMs enable adversaries to launch tailored attacks on a user-by-user basis. On the exploitation front, instead of human attackers manually searching for one difficult-to-identify bug in a product with millions of users, LLMs can find thousands of easy-to-identify bugs in products with thousands of users. And on the monetization front, instead of generic ransomware that always performs the same attack (encrypt all your data and request payment to decrypt), an LLM-driven ransomware attack could tailor the ransom demand based on the particular content of each exploited device. We show that these two attacks (and several others) are imminently practical using state-of-the-art LLMs. For example, we show that without any human intervention, an LLM finds highly sensitive personal information in the Enron email dataset (e.g., an executive having an affair with another employee) that could be used for blackmail. While some of our attacks are still too expensive to scale widely today, the incentives to implement these attacks will only increase as LLMs get cheaper. Thus, we argue that LLMs create a need for new defense-in-depth approaches.

cs.CR↗

arXiv2025

Privacy Auditing of Large Language Models

Current techniques for privacy auditing of large language models (LLMs) have limited efficacy -- they rely on basic approaches to generate canaries which leads to weak membership inference attacks that in turn give loose lower bounds on the empirical privacy leakage. We develop canaries that are far more effective than those used in prior work under threat models that cover a range of realistic settings. We demonstrate through extensive experiments on multiple families of fine-tuned LLMs that our approach sets a new standard for detection of privacy leakage. For measuring the memorization rate of non-privately trained LLMs, our designed canaries surpass prior approaches. For example, on the Qwen2.5-0.5B model, our designed canaries achieve $49.6\%$ TPR at $1\%$ FPR, vastly surpassing the prior approach's $4.2\%$ TPR at $1\%$ FPR. Our method can be used to provide a privacy audit of $\varepsilon \approx 1$ for a model trained with theoretical $\varepsilon$ of 4. To the best of our knowledge, this is the first time that a privacy audit of LLM training has achieved nontrivial auditing success in the setting where the attacker cannot train shadow models, insert gradient canaries, or access the model at every iteration.

cs.CR↗

arXiv2025

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses

We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench directly measures LLMs' success on tasks regularly performed by machine learning security experts. This approach offers a significant advantage: if a LLM could solve the challenges presented in bench, it would immediately present practical utility for adversarial machine learning researchers. We then design a strong agent that is capable of breaking 75% of CTF-like ("homework exercise") adversarial example defenses. However, we show that this agent is only able to succeed on 13% of the real-world defenses in our benchmark, indicating the large gap between difficulty in attacking "real" code, and CTF-like code. In contrast, a stronger LLM that can attack 21% of real defenses only succeeds on 54% of CTF-like defenses. We make this benchmark available at https://github.com/ethz-spylab/AutoAdvExBench.

cs.CR↗

arXiv2025

Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards

It is now common to evaluate Large Language Models (LLMs) by having humans manually vote to evaluate model outputs, in contrast to typical benchmarks that evaluate knowledge or skill at some particular task. Chatbot Arena, the most popular benchmark of this type, ranks models by asking users to select the better response between two randomly selected models (without revealing which model was responsible for the generations). These platforms are widely trusted as a fair and accurate measure of LLM capabilities. In this paper, we show that if bot protection and other defenses are not implemented, these voting-based benchmarks are potentially vulnerable to adversarial manipulation. Specifically, we show that an attacker can alter the leaderboard (to promote their favorite model or demote competitors) at the cost of roughly a thousand votes (verified in a simulated, offline version of Chatbot Arena). Our attack consists of two steps: first, we show how an attacker can determine which model was used to generate a given reply with more than $95\%$ accuracy; and then, the attacker can use this information to consistently vote for (or against) a target model. Working with the Chatbot Arena developers, we identify, propose, and implement mitigations to improve the robustness of Chatbot Arena against adversarial manipulation, which, based on our analysis, substantially increases the cost of such attacks. Some of these defenses were present before our collaboration, such as bot protection with Cloudflare, malicious user detection, and rate limiting. Others, including reCAPTCHA and login are being integrated to strengthen the security in Chatbot Arena.

cs.LG↗

arXiv2024

On Evaluating the Durability of Safeguards for Open-Weight LLMs

Stakeholders -- from model developers to policymakers -- seek to minimize the dual-use risks of large language models (LLMs). An open challenge to this goal is whether technical safeguards can impede the misuse of LLMs, even when models are customizable via fine-tuning or when model weights are fully open. In response, several recent studies have proposed methods to produce durable LLM safeguards for open-weight LLMs that can withstand adversarial modifications of the model's weights via fine-tuning. This holds the promise of raising adversaries' costs even under strong threat models where adversaries can directly fine-tune model weights. However, in this paper, we urge for more careful characterization of the limits of these approaches. Through several case studies, we demonstrate that even evaluating these defenses is exceedingly difficult and can easily mislead audiences into thinking that safeguards are more durable than they really are. We draw lessons from the evaluation pitfalls that we identify and suggest future research carefully cabin claims to more constrained, well-defined, and rigorously examined threat models, which can provide more useful and candid assessments to stakeholders.

cs.CR↗

arXiv2024

SoK: Watermarking for AI-Generated Content

As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of distinguishing between AI and human-generated content. These schemes embed hidden signals within AI-generated content to enable reliable detection. While watermarking is not a silver bullet for addressing all risks associated with GenAI, it can play a crucial role in enhancing AI safety and trustworthiness by combating misinformation and deception. This paper presents a comprehensive overview of watermarking techniques for GenAI, beginning with the need for watermarking from historical and regulatory perspectives. We formalize the definitions and desired properties of watermarking schemes and examine the key objectives and threat models for existing approaches. Practical evaluation strategies are also explored, providing insights into the development of robust watermarking techniques capable of resisting various attacks. Additionally, we review recent representative works, highlight open challenges, and discuss potential directions for this emerging field. By offering a thorough understanding of watermarking in GenAI, this work aims to guide researchers in advancing watermarking methods and applications, and support policymakers in addressing the broader implications of GenAI.

cs.CR↗