Jailbreak Detection on JBShield PAIR attack for Llama-3-8B
77Detection AccuracyJBShield-D
Evaluation Results
| Method | Links | |
|---|---|---|
| JBShield-DTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.05 | 77 | |
| RTVTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.05 | 58 |