Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Detection on JailbreakV
Loading...
99.69
AUROC
Mahal-OOD
59.1612
69.6831
80.205
90.7269
Dec 12, 2025
AUROC
AUPRC
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
AUPRC
Mahal-OOD
Model=LLaVA, Uses targ...
2025.12
99.69
99.11
Mahal-OOD*
Model=FLAVA, Uses targ...
2025.12
99.06
97.25
KNN-OOD
Model=LLaVA, Uses targ...
2025.12
98.33
95.88
KNN-OOD*
Model=FLAVA, Uses targ...
2025.12
95
86.49
JailDAM*
Model=CLIP, Uses targe...
2025.12
94.65
94.64
GradSafe
Model=LLaVA
2025.12
90.82
88.16
LLaVaGuard
Model=Qwen
2025.12
84.26
85.89
HiddenDetect
Model=LLaVA
2025.12
83.3
87.7
VLGuard
Model=LLaVA
2025.12
60.72
64.74
Feedback
Search any
task
Search any
task