Most Cited 2025 by Mateusz Dziemian Papers
2 papers found
Conference
#1
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian et al.
ICLR 2025arXiv:2410.09024
143
citations
#2
Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
Andy Zou, Maxwell Lin, Eliot Jones et al.
NEURIPS 2025arXiv:2507.20526
7
citations