Jailbreak Attack on JailbreakBenchmark
0.78ASR (m)S-PIEL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| S-PIELTarget Model Type=Mistral 7B2025.03 | 0.78 | 0.812 | |
| S-PIELTarget Model Type=Gemma-2-9B2025.03 | 0.7 | 0.72 | |
| S-PIELTarget Model Type=Llama-2-7B2025.03 | 0.67 | 0.726 | |
| S-PIELTarget Model Type=Llama-3.1-8B2025.03 | 0.43 | 0.462 | |
| S-PIELTarget Model Type=Llama-3.1-8B (DeepSeek-R1-Distilled)2025.03 | 0.38 | 0.413 | |
| GCGTarget Model Type=Mistral 7B2025.03 | 0.29 | 0.324 | |
| GCGTarget Model Type=Gemma-2-9B2025.03 | 0.08 | 0.1 | |
| GCGTarget Model Type=Llama-2-7B2025.03 | 0.01 | 0.017 | |
| Vanilla PromptTarget Model Type=Llama-2-7B2025.03 | 0 | 0 | |
| Vanilla PromptTarget Model Type=Llama-3.1-8B2025.03 | 0 | 0 | |
| GCGTarget Model Type=Llama-3.1-8B2025.03 | 0 | 0 | |
| Vanilla PromptTarget Model Type=Mistral 7B2025.03 | 0 | 0 | |
| Vanilla PromptTarget Model Type=Gemma-2-9B2025.03 | 0 | 0 | |
| Vanilla PromptTarget Model Type=Llama-3.1-8B (DeepSeek-R1-Distilled)2025.03 | 0 | 0 | |
| GCGTarget Model Type=Llama-3.1-8B (DeepSeek-R1-Distilled)2025.03 | 0 | 0 |