Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Attack on JailbreakBench GCG
Loading...
0.58
ASR
None
-0.0232
0.1334
0.29
0.4466
Jan 30, 2024
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
None
Model=Vicuna
2024.01
0.58
Perplexity Filter
Model=Vicuna
2024.01
0.14
None
Model=Llama-2
2024.01
0.02
SmoothLLM
Model=Vicuna
2024.01
0.01
SmoothLLM
Model=Llama-2
2024.01
0.01
Perplexity Filter
Model=Llama-2
2024.01
0.01
Rephrasing
Model=Vicuna
2024.01
0.01
RPO
Model=Vicuna
2024.01
0.01
Rephrasing
Model=Llama-2
2024.01
0
RPO
Model=Llama-2
2024.01
0
Feedback
Search any
task
Search any
task