NUWA 风险评测 · 评测基准
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
NUWA 研究解读 · 独立复核待完成
NUWA Research Note
研究问题研究设计与假设来源发现NUWA 解读局限与相反证据研究与决策意义机构与角色原始资源模型辅助整理 · 选读原始全文或官方文章中的相关章节；尚未完成逐章节审计。
研究速读
NUWA 解读：不拒绝与成功完成恶意工具任务是不同结果。
研究问题
防护能否阻止多步滥用，同时不只是破坏智能体能力？
研究设计与假设
AgentHarm 含十一类110项恶意任务，增强后440项，采用合成工具和逐任务判分。
来源发现
所报GPT-4o伤害得分在受测攻击下从48.4%升至72.7%。
拒绝率从48.9%降至13.6%，两者指标不同（§4.2）。
NUWA 解读
NUWA 解读：不拒绝与成功完成恶意工具任务是不同结果。
局限与相反证据
判分绑定定制合成工具，不能直接迁移到其他工具与框架（§5）。
研究与决策意义
模型建议：同时核对恶意完成与良性能力，并标注具体攻击条件。
精确来源位置
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents · AbstractSelected original resource https://arxiv.org/html/2410.09024v3; sha256:df646fcb08130ba2d9278560fdfab308fd50491576fbb391ad6843a8697a886a; archived source capture; exact capture time not independently established
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents · §3.1 Overview of AgentHarmSelected original resource https://arxiv.org/html/2410.09024v3; sha256:df646fcb08130ba2d9278560fdfab308fd50491576fbb391ad6843a8697a886a; archived source capture; exact capture time not independently established
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents · §4.2 Main ResultsSelected original resource https://arxiv.org/html/2410.09024v3; sha256:df646fcb08130ba2d9278560fdfab308fd50491576fbb391ad6843a8697a886a; archived source capture; exact capture time not independently established
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents · §5 DiscussionSelected original resource https://arxiv.org/html/2410.09024v3; sha256:df646fcb08130ba2d9278560fdfab308fd50491576fbb391ad6843a8697a886a; archived source capture; exact capture time not independently established
来源核查、数据提取、编辑批准与实验复现分别记录。 方法说明 →
机构与角色
作者 (14)
Maksym Andriushchenko · Alexandra Souly · Mateusz Dziemian · Derek Duenas · Maxwell Lin · Justin Wang · Dan Hendrycks · Andy Zou · Zico Kolter · Matt Fredrikson · Eric Winsor · Jerome Wynne · Yarin Gal · Xander Davies
评测协议
引用与复用
引用研究发现时请引用原始出版物；引用 NUWA 的整理与解释时，单独引用本站记录及对应快照。
原始出版物 · BibTeX
@misc{agentharm,
title = {AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents},
url = {https://arxiv.org/abs/2410.09024v3},
author = {Maksym Andriushchenko and Alexandra Souly and Mateusz Dziemian and Derek Duenas and Maxwell Lin and Justin Wang and Dan Hendrycks and Andy Zou and Zico Kolter and Matt Fredrikson and Eric Winsor and Jerome Wynne and Yarin Gal and Xander Davies},
year = {2024},
date = {2024-10-11},
version = {arXiv:2410.09024v3},
note = {arXiv:2410.09024v3}
}
NUWA 记录 · BibTeX
@misc{agentharm-nuwa,
title = {AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents — NUWA research record},
url = {https://whitzard.tech/nuwa/whitzard-index/work/agentharm/},
version = {2026-10-29.1},
organization = {NUWA Frontier AI Safety Lab},
howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--agentharm.json},
note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--agentharm.json.}
}
证据快照 2026-10-29.1 · 索引更新 · RSS
参考文献
- [1] Maksym Andriushchenko, Alexandra Souly 等. AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents. 2025-04-18. v3 [arXiv]; Author affiliations on the original paper title page; Abstract; §3.1 Overview of AgentHarm