Jailbreak Detection on JBShield evaluation suite for Llama-3-8B
96Detection AccuracyRTV
Evaluation Results
| Method | Links | |
|---|---|---|
| RTVTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.05 | 96 | |
| JBShield-DTarget Model=Llama-3-8B, n (Sample Size)=50, FPR Threshold=5%2026.05 | 91 |