Jailbreak Attack on ForbiddenQuestions 13 (test)
0.0231ASRDirect
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DirectVictim Model=Qwen3-4B-Instruct-2507, tau=150, alpha=5, beta=0.52026.02 | 0.0231 | 1.5552 | |
| DirectVictim Model=Llama-3.1-8B-Instruct, tau=150, alpha=0.8, beta=0.52026.02 | 0.0641 | 1.5907 | |
| DirectVictim Model=Qwen2.5-7B-Instruct, tau=150, alpha=6.5, beta=0.52026.02 | 0.0833 | 1.9677 | |
| ShallowJailVictim Model=Qwen2.5-7B-Instruct, tau=150, alpha=6.5, beta=0.52026.02 | 0.4872 | 4.8335 | |
| ShallowJailVictim Model=Qwen3-4B-Instruct-2507, tau=150, alpha=5, beta=0.52026.02 | 0.5718 | 4.6646 | |
| ShallowJailVictim Model=Llama-3.1-8B-Instruct, tau=150, alpha=0.8, beta=0.52026.02 | 0.5833 | 14.5508 |