arXiv Artificial Intelligence

Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks

1 hour ago 05.10.2026 07:00 👁 1 views
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks

Quick summary

arXiv:2610.03585v1 Announce Type: cross Abstract: Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the agent. In this paper, we explore whether it also influences the benchmark's measurement. To measure the effect of the benchmark representation, we introduce threat-preserving representation sensitivity (TPRS), which measures how much the ASR changes when we change the agent-visible representation while holding

Key takeaways

  • arXiv:2610.03585v1 Announce Type: cross Abstract: Security benchmarks for LLM-based agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the agent.
  • In this paper, we explore whether it also influences the benchmark's measurement.
  • To measure the effect of the benchmark representation, we introduce threat-preserving representation sensitivity (TPRS), which measures how much the ASR changes when we change the agent-visible representation while holding

Why it matters

“Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks” shows why AI risk cannot be reduced to answer accuracy. Access controls, logging, human approval and incident response need to be designed into the workflow from the start.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗