Related papers: OS-Harm: A Benchmark for Measuring Safety of Compu…

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against…

Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new risks for sensitive information leakage. We introduce…

Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted…

The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimension of anti-detection. We argue that for agents to survive…

The integration of tool use into large language models (LLMs) enables agentic systems with real-world impact. In the meantime, unlike standalone LLMs, compromised agents can execute malicious workflows with more consequential impact,…

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets…

Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity…

Large language models (LLM) are perceived to offer promising potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the…

Agents operating with computer and Web use inevitably encounter errors: inaccessible webpages, missing files, local and remote misconfigurations, etc. These errors do not thwart agents based on state-of-the-art models. They helpfully…

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt trigger this behaviour, and which do not. We present a systematic taxonomy based on…

The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product…

The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs'…

Autonomous agents that navigate Graphical User Interfaces (GUIs) to automate tasks like document editing and file management can greatly enhance computer workflows. While existing research focuses on online settings, desktop environments,…

As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trustworthy deployment in…

Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call workflows rather than text generation alone. While recent benchmarks evaluate agents across diverse environments and risk…

AI agents have significant potential to reshape cybersecurity, making a thorough assessment of their capabilities critical. However, existing evaluations fall short, because they are based on small-scale benchmarks and only measure static…