Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Attack on JailbreakBench PAIR
Loading...
82
Attack Success Rate (ASR)
None
-3.28
18.86
41
63.14
Jan 30, 2024
Attack Success Rate (ASR)
Updated 4d ago
Evaluation Results
Method
Method
Links
Attack Success Rate (ASR)
None
Model=Vicuna
2024.01
82
Perplexity Filter
Model=Vicuna
2024.01
81
SmoothLLM
Model=Vicuna
2024.01
47
Rephrasing
Model=Vicuna
2024.01
25
RPO
Model=Vicuna
2024.01
20
None
Model=Llama-2
2024.01
4
Perplexity Filter
Model=Llama-2
2024.01
4
Rephrasing
Model=Llama-2
2024.01
4
SmoothLLM
Model=Llama-2
2024.01
1
RPO
Model=Llama-2
2024.01
0
Feedback
Search any
task
Search any
task