2025 "prompt injection attacks" Papers
2 papers found
DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
Hao Li, Xiaogeng Liu, CHIU Chun et al.
NeurIPS 2025posterarXiv:2506.12104
10
citations
OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
Thomas Kuntz, Agatha Duzan, Hao Zhao et al.
NeurIPS 2025spotlightarXiv:2506.14866
18
citations