Related papers: Cross-Session Threats in AI Agents: Benchmark, Eva…

Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files, tools, memory, and execution environments. However, this modularity introduces attack surfaces…

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we…

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in…

The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current guardrail models lack agentic risk awareness and transparency in risk diagnosis. To introduce…

Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural…

Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks…

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly…

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and unstructured inter-agent communication introduces severe risks, such as indirect prompt…

Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables autonomy, it also expands the attack surface for backdoor threats. Backdoor triggers…

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…

Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via…

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors…

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails.…

As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…