Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
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 measur...
Neeraj Karamchandani, Piyush Nagasubramaniam, Xin-Hong Xie et al.
· 0 citations