NSFW Content Moderation on Malicious NSFW datasets
1.5Unsafe Ratio (Sexually Explicit)
PromptGuard
Updated 4d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.01 | 1.5 | 5.17 | 12.17 | 4.5 | 5.84 | |
2025.01 | 2.2 | 24.5 | 38.67 | 12.83 | 19.1 | |
2025.01 | 4.33 | 8.17 | 29.83 | 7.83 | 12.54 | |
2025.01 | 15.67 | 25.33 | 32.17 | 16.17 | 22.34 | |
2025.01 | 36.33 | 9.67 | 37.33 | 8.33 | 22.92 | |
2025.01 | 41.83 | 13.83 | 35.67 | 8.33 | 24.92 | |
2025.01 | 45.17 | 18.5 | 34.67 | 13.17 | 27.88 | |
2025.01 | 45.67 | 33.83 | 38.83 | 19.67 | 34.5 | |
2025.01 | 71.17 | 30 | 36.17 | 19.5 | 39.21 |