Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Read the original on arXiv AI →The paper introduces threat‑preserving representation sensitivity (TPRS) to assess how changes in agent‑visible wording affect attack success rates (ASR) while keeping the underlying task and evaluation criteria constant. Experiments on Agent Security Bench, MCPTox, and AgentDojo show that renaming threat‑related tools can significantly alter ASR—up to +13.21 percentage points on some models—yet may also degrade benign utility. The findings suggest that security scores based on a single representation may not generalize, urging robustness claims to be validated across multiple threat‑preserving representations.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.