Adversarial Attack on Mistral 7B
100ASRSRA
Evaluation Results
| Method | Links | |
|---|---|---|
| SRASource Model=Mistral 7B, Optimization Time=15s, Attack Setting=White-box2026.05 | 100 | |
| SRASource Model=Mistral 7B, Optimization Time=30s, Attack Setting=White-box2026.05 | 99.81 | |
| SRASource Model=Mistral 7B, Optimization Time=60s, Attack Setting=White-box2026.05 | 99.81 | |
| SRASource Model=Vicuna 13B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 99.62 | |
| SRASource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 99.23 | |
| SRASource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 99.23 | |
| SRASource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 98.85 | |
| SRASource Model=Vicuna 13B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 98.85 | |
| SRASource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 98.85 | |
| SRASource Model=Vicuna 13B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 98.65 | |
| SRASource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 98.65 | |
| SRASource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 98.27 | |
| AutoDANSource Model=Mistral 7B, Optimization Time=60s, Attack Setting=White-box2026.05 | 98.27 | |
| AutoDANSource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 98.27 | |
| AutoDANSource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 98.08 | |
| AutoDANSource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 98.08 | |
| AutoDANSource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 97.5 | |
| AutoDANSource Model=Mistral 7B, Optimization Time=15s, Attack Setting=White-box2026.05 | 97.31 | |
| AutoDANSource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 97.31 | |
| AutoDANSource Model=Vicuna 13B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 97.12 | |
| AutoDANSource Model=Mistral 7B, Optimization Time=30s, Attack Setting=White-box2026.05 | 97.12 | |
| AutoDANSource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 96.73 | |
| AutoDANSource Model=Vicuna 13B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 96.73 | |
| AutoDANSource Model=Vicuna 13B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 95.19 | |
| BEASTSource Model=Mistral 7B, Optimization Time=60s, Attack Setting=White-box2026.05 | 57.12 | |
| BEASTSource Model=Mistral 7B, Optimization Time=30s, Attack Setting=White-box2026.05 | 50 | |
| BEASTSource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 45.58 | |
| BEASTSource Model=Mistral 7B, Optimization Time=15s, Attack Setting=White-box2026.05 | 42.12 | |
| BEASTSource Model=Vicuna 13B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 41.15 | |
| BEASTSource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 40.58 | |
| BEASTSource Model=Vicuna 13B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 34.62 | |
| BEASTSource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 33.85 | |
| BEASTSource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 31.73 | |
| BEASTSource Model=Vicuna 13B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 29.62 | |
| BEASTSource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 28.85 | |
| GCGSource Model=Mistral 7B, Optimization Time=60s, Attack Setting=White-box2026.05 | 26.15 | |
| GCGSource Model=Mistral 7B, Optimization Time=30s, Attack Setting=White-box2026.05 | 25 | |
| BEASTSource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 25 | |
| GCGSource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 24.81 | |
| GCGSource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.05 | 24.81 | |
| GCGSource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 23.65 | |
| GCGSource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 22.69 | |
| GCGSource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.05 | 21.54 | |
| GCGSource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.05 | 21.15 | |
| GCGSource Model=Mistral 7B, Optimization Time=15s, Attack Setting=White-box2026.05 | 18.65 |