Attack Detection on Harmful Attacks 105K sample set
97.4Detection Rate
LlamaGuard
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 97.4 | |
2026.02 | 85.8 | |
2026.02 | 68 | |
2026.02 | 67 | |
2026.02 | 37.3 | |
2026.02 | 36.7 | |
2026.02 | 27.4 | |
2026.02 | 7.1 |
LlamaGuard
| Method | Links | |
|---|---|---|
2026.02 | 97.4 | |
2026.02 | 85.8 | |
2026.02 | 68 | |
2026.02 | 67 | |
2026.02 | 37.3 | |
2026.02 | 36.7 | |
2026.02 | 27.4 | |
2026.02 | 7.1 |