List your company
ResearchFormerly WizWand

Adversarial Jailbreak Attack on Vicuna 13B

98.65Attack Success Rate (ASR)SRA
-2.146824.021650.1976.3584May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SRASource Model=Mistral 7B, Optimization Time=60s, Attack Setting=Black-box2026.0598.65——
SRASource Model=Mistral 7B, Optimization Time=30s, Attack Setting=Black-box2026.0596.92——
SRASource Model=Mistral 7B, Optimization Time=15s, Attack Setting=Black-box2026.0595.38——
SRABudget=60s2026.0593.0820.8189.62
SRASource Model=Vicuna 13B, Optimization Time=60s, Attack Setting=White-box2026.0593.08——
SRABudget=30s2026.0588.4623.2287.69
SRASource Model=Vicuna 13B, Optimization Time=30s, Attack Setting=White-box2026.0588.46——
SRASource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.0587.88——
SRASource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.0586.92——
SRABudget=15s2026.0586.7325.4385.19
SRASource Model=Vicuna 13B, Optimization Time=15s, Attack Setting=White-box2026.0586.73——
BEASTBudget=60s, Venue=ICML 20242026.0584.8101.7329.04
BEASTSource Model=Vicuna 13B, Optimization Time=60s, Attack Setting=White-box2026.0584.8——
SRASource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.0584.42——
SRASource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.0580.19——
SRASource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.0579.62——
SRASource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.0579.42——
BEASTBudget=30s, Venue=ICML 20242026.0564.0470.632.88
BEASTSource Model=Vicuna 13B, Optimization Time=30s, Attack Setting=White-box2026.0564.04——
AutoDANSource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.0553.08——
AutoDANSource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.0552.12——
AutoDANSource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.0551.15——
AutoDANSource Model=Mistral 7B, Optimization Time=30s, Attack Setting=Black-box2026.0550.77——
AutoDANSource Model=Mistral 7B, Optimization Time=15s, Attack Setting=Black-box2026.0550.58——
AutoDANSource Model=Mistral 7B, Optimization Time=60s, Attack Setting=Black-box2026.0549.23——
AutoDANBudget=15s, Venue=ICLR 20242026.0539.2755.4434.42
AutoDANSource Model=Vicuna 13B, Optimization Time=15s, Attack Setting=White-box2026.0539.27——
AutoDANBudget=30s, Venue=ICLR 20242026.0538.4655.8438.27
AutoDANSource Model=Vicuna 13B, Optimization Time=30s, Attack Setting=White-box2026.0538.46——
AutoDANBudget=60s, Venue=ICLR 20242026.0538.2761.5531.73
AutoDANSource Model=Vicuna 13B, Optimization Time=60s, Attack Setting=White-box2026.0538.27——
BEASTBudget=15s, Venue=ICML 20242026.0537.6950.4523.85
BEASTSource Model=Vicuna 13B, Optimization Time=15s, Attack Setting=White-box2026.0537.69——
AutoDANSource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.0529.23——
AutoDANSource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.0528.46——
AutoDANSource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.0527.31——
BEASTSource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.0519.23——
BEASTSource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.0517.88——
BEASTSource Model=Mistral 7B, Optimization Time=60s, Attack Setting=Black-box2026.0516.35——
BEASTSource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.0515.77——
BEASTSource Model=Mistral 7B, Optimization Time=15s, Attack Setting=Black-box2026.0514.23——
BEASTSource Model=Mistral 7B, Optimization Time=30s, Attack Setting=Black-box2026.0514.04——
BEASTSource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.058.46——
BEASTSource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.055.77——
GCGSource Model=Guanaco 7B, Optimization Time=60s, Attack Setting=Black-box2026.055.58——
GCGSource Model=Vicuna 7B, Optimization Time=30s, Attack Setting=Black-box2026.055.19——
GCGSource Model=Vicuna 7B, Optimization Time=60s, Attack Setting=Black-box2026.055.19——
GCGSource Model=Guanaco 7B, Optimization Time=30s, Attack Setting=Black-box2026.055——
GCGSource Model=Mistral 7B, Optimization Time=60s, Attack Setting=Black-box2026.054.42——
GCGSource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.054.04——
BEASTSource Model=Guanaco 7B, Optimization Time=15s, Attack Setting=Black-box2026.053.46——
GCGSource Model=Mistral 7B, Optimization Time=30s, Attack Setting=Black-box2026.053.27——
GCGSource Model=Vicuna 7B, Optimization Time=15s, Attack Setting=Black-box2026.052.88——
CleanBudget=-2026.051.9217.71.54
GCGSource Model=Mistral 7B, Optimization Time=15s, Attack Setting=Black-box2026.051.73——