Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Attack Success Rate on JBShield (test)
Loading...
95
Attack Success Rate (ASR)
JB-GCG
90.25
92.625
95
97.375
May 4, 2026
Attack Success Rate (ASR)
Toxic Detection Rate
Jailbreak Detection Rate
ASR (Direct)
ASR (Masked)
Updated 28d ago
Evaluation Results
Method
Method
Links
Attack Success Rate (ASR)
Toxic Detection Rate
Jailbreak Detection Rate
ASR (Direct)
ASR (Masked)
JB-GCG
l_dir=18, l_opt=18
2026.05
95
0
100
48.4
26.3
Feedback
Search any
task
Search any
task
