dreadnode/AIRTBench
收藏Hugging Face2025-06-17 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/dreadnode/AIRTBench
下载链接
链接失效反馈官方服务：
资源简介：
AIRTBench数据集是一个评估语言模型在自主发现和利用AI/ML安全漏洞能力的AI红队基准测试的数据集。该数据集包含12种不同语言模型在70个安全挑战上的8066次实验运行结果。
The AIRTBench dataset is a benchmark for evaluating language models ability to autonomously discover and exploit AI/ML security vulnerabilities. It contains the experimental results of 12 different language models on 70 security challenges across 8,066 runs.
提供机构：
dreadnode
