exploitgym
B待确认Benchmark安全对齐越狱攻防开放
发布方：sunblaze-ucb
热度11.2±0
下载量 · 30天
—
Hugging Face
GitHub Stars
842
代码仓库
论文被引
—
Semantic Scholar
跑分模型 · 30天
—
Leaderboard results
简介
ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.