中文

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard

密码学与安全 2026-05-22 v1 人工智能

摘要

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.

关键词

引用

@article{arxiv.2605.22568,
  title  = {Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard},
  author = {Sahar Abdelnabi and Chris Hicks and Konrad Rieck and Ahmad-Reza Sadeghi},
  journal= {arXiv preprint arXiv:2605.22568},
  year   = {2026}
}