OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

17 June 2025

Thomas Kuntz

Agatha Duzan

Hao Zhao

Francesco Croce

Zico Kolter

Nicolas Flammarion

Maksym Andriushchenko

ArXiv (abs)PDF HTML

Papers citing "OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents"

Title
No papers