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

VLM Jailbreak

Benchmarks

Task NameDataset NameSOTA ResultTrend
VLM Jailbreak DetectionVLM Jailbreak Average (MM-SafetyBench, FigImg, JailBreakV-28K)
Average AUROC0.94
14
Showing 1 of 1 rows