JailJudge

Evals

Benchmark / dataset

Jailbreak judge benchmark with explanations.

Category
Jailbreak & misuse
Insurance exposure
Regulatory/bias
Publisher
HKUST
Publisher type
Academic
License
MIT
Status
Stale (>12mo)
Last commit
2024-12-13
Stars
67

View source on GitHub →

Wanich Risk Lab, 2026.