List your company

Jailbreak Detection on JBShield AutoDAN attack for Llama-3-8B

97Detection AccuracyJBShield-D
7177.7584.591.25May 4, 2026

Evaluation results

MethodLinks
JBShield-DTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.0597
RTVTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.0572