Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Jailbreak Detection on AdvBench Vicuna-7B
Loading...
95.7
AUROC
MTK
19.676
39.413
59.15
78.887
Jun 5, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
MTK
Attack=AutoDAN
2026.06
95.7
SelfDefend
Attack=AutoDAN
2026.06
94.3
MTK
Attack=Avg.
2026.06
92.3
HiddenDetect
Attack=Avg.
2026.06
89.5
HiddenDetect
Attack=AutoDAN
2026.06
87.5
SelfDefend
Attack=Avg.
2026.06
85.5
HSF
Attack=Avg.
2026.06
71
GradCuff
Attack=Avg.
2026.06
66.8
GradCuff
Attack=AutoDAN
2026.06
63.5
SaP
Attack=AutoDAN
2026.06
58.4
SmoothLLM
Attack=Avg.
2026.06
57.8
SmoothLLM
Attack=AutoDAN
2026.06
53.5
SaP
Attack=Avg.
2026.06
53.2
GradSafe
Attack=AutoDAN
2026.06
49.7
GradSafe
Attack=Avg.
2026.06
38
HSF
Attack=AutoDAN
2026.06
22.6
Feedback
Search any
task
Search any
task