Mateusz Dziemian

According to our database, Mateusz Dziemian authored at least 5 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition.

Andy Zou, Maxwell Lin, Eliot Krzysztof Jones, Micha Nowak, Mateusz Dziemian, Nick Winter, Alexander Grattan, Valent Nathanael, Ayla Croft, Xander Davies, Jai Patel, Robert Kirk, Nate Burnikell, Yarin Gal, Dan Hendrycks, J. Zico Kolter, Matt Fredrikson

CoRR, July, 2025

Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems.

Simon Lermen, Mateusz Dziemian, Natalia Pérez-Campanero Antolín

CoRR, April, 2025

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, J. Zico Kolter, Matt Fredrikson, Yarin Gal, Xander Davies

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Applying Refusal-Vector Ablation to Llama 3.1 70B Agents.

Simon Lermen, Mateusz Dziemian, Govind Pimpale

CoRR, 2024

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, Zico Kolter, Matt Fredrikson, Eric Winsor, Jerome Wynne, Yarin Gal, Xander Davies

CoRR, 2024