Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks

Paper recorded by Signals 4 on 2026-10-02 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-02 on arXiv · recorded by Signals 4 on 2026-10-05

Category: cs.AI · 人工智能 · first seen 2026-10-05

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 thr

Read on arXiv →