Text-to-Image Jailbreak Attack on NSFW-200
100Attack Success Rate (Paper)SneakyPrompt
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SneakyPromptEvaluation Metric=Bypass Rate, Code Ref=YES, Victim Model=SDv1.4, ρ (LoC difference)=-10752026.06 | 100 | 100 | 0 | |
| JailFuzzerEvaluation Metric=Bypass Rate, Code Ref=YES, Victim Model=SDv1.4, ρ (LoC difference)=-13092026.06 | 100 | 100 | 0 | |
| PGJEvaluation Metric=ASR-1, Code Ref=NO, Victim Model=SDXL, ρ (LoC difference)=-2026.06 | 100 | 92.8 | 7.2 |