The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents---which use external tools and can execute multi-stage tasks---may pose a greater risk if misused, but their robustness remains underexplored. To facilitate research on LLM agent misuse, we propose a new benchmark called AgentHarm. The benchmark includes a diverse set of 110 explicitly malicious agent tasks (440 with augmentations), covering 11 harm categories including fraud, cybercrime, and harassment. In addition to measuring whether models refuse harmful agentic requests, scoring well on AgentHarm requires jailbroken agents to maintain their capabilities following an attack to complete a multi-step task. We evaluate a range of leading LLMs, and find (1) leading LLMs are surprisingly complaint with malicious agent requests without jailbreaking, (2) simple universal jailbreak strings can be adapted to effectively jailbreak agents, and (3) these jailbreaks enable coherent and malicious multi-step agent behavior and retain model capabilities. To enable simple and reliable evaluation of attacks and defenses for LLM-based agents, we publicly release AgentHarm at https://huggingface.co/datasets/ai-safety-institute/AgentHarm.

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after hundreds of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that progress on tamper-resistance is possible, opening up a promising new avenue to improve the safety and security of open-weight LLMs.

AI agents are rapidly being deployed across diverse industries, but can they adhere to deployment policies under attacks? We organized a one-month red teaming challenge---the largest of its kind to date---involving expert red teamers attempting to elicit policy violations from AI agents powered by $22$ frontier LLMs. Our challenge collected $1.8$ million prompt injection attacks, resulting in over $60,000$ documented successful policy violations, revealing critical vulnerabilities. Utilizing this extensive data, we construct a challenging AI agent red teaming benchmark, currently achieving near $100\%$ attack success rates across all tested agents and associated policies. Our further analysis reveals high transferability and universality of successful attacks, underscoring the scale and criticality of existing AI agent vulnerabilities. We also observe minimal correlation between agent robustness and factors such as model capability, size, or inference compute budget, highlighting the necessity of substantial improvements in defense. We hope our benchmark and insights drive further research toward more secure and reliable AI agents.

Large language models (LLMs) have achieved impressive performance on code generation. However, for complex programming tasks, generating the correct solution in one go becomes challenging, thus some prior works have designed program repair approaches to improve code generation performance. In this work, we propose self-debugging, which teaches a large language model to debug its predicted program. In particular, we demonstrate that self-debugging can teach the large language model to perform rubber duck debugging; i.e., without any human feedback on the code correctness or error messages, the model is able to identify its mistakes by leveraging code execution and explaining the generated code in natural language. Self-debugging achieves the state-of-the-art performance on several code generation benchmarks, including the Spider dataset for text-to-SQL generation, TransCoder for C++-to-Python translation, and MBPP for text-to-Python generation. On the Spider benchmark where there are no unit tests to verify the correctness of predictions, self-debugging with code explanation consistently improves the baseline by 2-3%, and improves the prediction accuracy on problems of the hardest level by 9%. On TransCoder and MBPP where unit tests are available, self-debugging improves the baseline accuracy by up to 12%. Meanwhile, by leveraging feedback messages and reusing failed predictions, self-debugging notably improves sample efficiency, and can match or outperform baseline models that generate more than 10$\times$ candidate programs.

Third-party web cookies are often used for privacy-invasive behavior tracking. Partly due to privacy concerns, browser vendors have started to block all third-party cookies in recent years. To understand the effects of such third-party cookieless browsing, we crawled and measured the top 10,000 Tranco websites. We developed a framework to remove third-party cookies and analyze the differences between the appearance of web pages with and without these cookies. We find that disabling third-party cookies has no substantial effect on website appearance including layouts, text, and images. This validates the industry-wide shift towards cookieless browsing as a way to protect user privacy without compromising on the user experience.

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with "circuit breakers." Existing techniques aimed at improving alignment, such as refusal training, are often bypassed. Techniques such as adversarial training try to plug these holes by countering specific attacks. As an alternative to refusal training and adversarial training, circuit-breaking directly controls the representations that are responsible for harmful outputs in the first place. Our technique can be applied to both text-only and multimodal language models to prevent the generation of harmful outputs without sacrificing utility -- even in the presence of powerful unseen attacks. Notably, while adversarial robustness in standalone image recognition remains an open challenge, circuit breakers allow the larger multimodal system to reliably withstand image "hijacks" that aim to produce harmful content. Finally, we extend our approach to AI agents, demonstrating considerable reductions in the rate of harmful actions when they are under attack. Our approach represents a significant step forward in the development of reliable safeguards to harmful behavior and adversarial attacks.