Jailbreak Attack on MM-SafetyBench GPT-4o
2.8Average ToxicityQR
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| QRAttack=QR2026.04 | 2.8 | 34.02 | 15.46 | 14.11 | 31.82 | 47.22 | 55.74 | 18.18 | 14.68 | 48.37 | 22.3 | 29.23 | 40.12 | 61.47 | 43.62 | 34.02 | |
| JPSAttack=JPS2026.04 | 3.39 | 50.83 | 46.82 | 38.57 | 44.91 | 66.43 | 68.74 | 34.26 | 19.31 | 56.48 | 41.73 | 49.65 | 53.98 | 79.36 | 60.54 | 50.83 | |
| MosaicAttack=Mosaic2026.04 | 4.13 | 69.66 | 78.35 | 65.03 | 61.36 | 86.81 | 77.05 | 63.64 | 27.52 | 64.71 | 66.91 | 72.31 | 65.27 | 95.41 | 81.21 | 69.66 |