Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

VLM Jailbreak Detection on FigImg

0.992AUROC

MTK

0.50320.63010.7570.8839Jun 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
0.992
2026.06
0.98
2026.06
0.959
2026.06
0.877
2026.06
0.855
2026.06
0.761
2026.06
0.716
2026.06
0.707
2026.06
0.685
2026.06
0.685
2026.06
0.671
2026.06
0.651
2026.06
0.634
2026.06
0.522