3 papers
cs.CR2026
Quantifying Frontier LLM Capabilities for Container Sandbox Escape
Rahul Marchand, Art O Cathain, Jerome Wynne +8
Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitiga…
cs.AI2026
Seven simple steps for log analysis in AI systems
Magda Dubois, Ekin Zorer, Maia Hamin +17
AI systems produce large volumes of logs as they interact with tools and users. Analysing these logs can help understand model capabilities, propensities, and behaviours, or assess…
cs.LG2025
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian +11
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 s…