arXiv 2610.13623 · cs.CR · 2026-10-09
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
Ziyi Yang, Adel Bibi, Guohao Li, Bernard Ghanem, Carlos Hinojosa
King Abdullah University of Science and Technology
在最新榜 #298 本站收录于 2026-10-21
一句话要点
APEX-Harm 在含上百个文件的共享工作区里，测试金融、咨询、法律 Agent 抵御提示和脚本注入的能力。
APEX-Harm tests finance, consulting and legal agents against prompt and script injection in large shared workspaces.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：安全与可解释
- Behavioral Compositionality of Sparse Autoencoder Representations ▲110
- DecepEval: A Benchmark for Evaluating Deception in LLM Agents ▲85
- Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics ▲55
- U-Space: Uncovering When and Why Uncertainty Arises in Language Models ▲54
- Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures ▲29
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。