HarmBench

档案区分来源方法阅读与既有目录信息；已经公开不代表完成独立证据复核或双语编辑复核。

测量构念

自动红队方法与防护能否采用统一的行为级判分比较？

任务与样本

框架标准化有害行为、生成及分类；所报研究比较18种攻击与33个目标模型或防护。

判分与失效情形

分类器判攻击成功，各功能类别判据不同。

系统条件

所报研究比较18攻击与33目标或防护。

统计含义

来源报告的结果表述；这不等同于已确定运行次数、分母或估计方法： 版权类采用比非版权分类器更严格的内容匹配判据（§6.1）。

效度与解释

功能类别判据不同，汇总成功率不能视为等价的真实伤害尺度。

适用研究问题

模型建议：比较攻击或防护时保留分类器及类别明细。

• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal · AbstractSelected original resource https://arxiv.org/html/2402.04249v2; sha256:c0222f5cb89e2f882de4cbb59e4d61897049528425e5e0cce1928bfb0655e37d; archived source capture; exact capture time not independently established
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal · §4 HarmBenchSelected original resource https://arxiv.org/html/2402.04249v2; sha256:c0222f5cb89e2f882de4cbb59e4d61897049528425e5e0cce1928bfb0655e37d; archived source capture; exact capture time not independently established
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal · §6.1 Main ResultsSelected original resource https://arxiv.org/html/2402.04249v2; sha256:c0222f5cb89e2f882de4cbb59e4d61897049528425e5e0cce1928bfb0655e37d; archived source capture; exact capture time not independently established
• HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal · §7 ConclusionSelected original resource https://arxiv.org/html/2402.04249v2; sha256:c0222f5cb89e2f882de4cbb59e4d61897049528425e5e0cce1928bfb0655e37d; archived source capture; exact capture time not independently established