Jailbreaking Attack Defense on MM-Safety-Bench Turn 2
0.58ASRFragGuard
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| FragGuardBackbone=GPT-4o, Toxicity Judge=Mistral-7B and Gemini 2.5-Flash2026.01 | 0.58 | 1.22 | 66.73 | |
| FragGuardBackbone=Gemini-2.0-Flash, Toxicity Judge=Mistral-7B and Gemini 2.5-Flash2026.01 | 0.97 | 1.26 | 69.31 | |
| FragGuardBackbone=LLaVa-7B, Toxicity Judge=Mistral-7B and Gemini 2.5-Flash2026.01 | 3.85 | 1.25 | 80.19 | |
| FragGuardBackbone=LLaVa-13B, Toxicity Judge=Mistral-7B and Gemini 2.5-Flash2026.01 | 9.04 | 1.68 | 24.23 | |
| FragGuardBackbone=Qwen-7B, Toxicity Judge=Mistral-7B and Gemini 2.5-Flash2026.01 | 10 | 1.5 | 16.54 |