Jailbreak Detection on Jailbreak Prompts
96.03AUROC
DE-FIVE
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 96.03 | |
2026.06 | 95.74 | |
2026.06 | 95.22 | |
2026.06 | 94.36 | |
2026.06 | 94.27 | |
2026.06 | 91.09 | |
2026.06 | 88.49 | |
2026.06 | 83.26 | |
2026.06 | 82.91 | |
2026.06 | 82.77 | |
2026.06 | 73.86 | |
2026.06 | 69.31 |