Jailbreak Detection on JBShield AutoDAN attack for Llama-3-8B
97Detection AccuracyJBShield-D
Evaluation Results
| Method | Links | |
|---|---|---|
| JBShield-DTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.05 | 97 | |
| RTVTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.05 | 72 |