Jailbreak Attack Success on STRONGREJECT 60 behaviors (train)
93EVUSIHO
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| IHOTarget model=Qwen-7B2026.06 | 93 | — | — | — | — | — | — | — | — | |
| IHOTarget model=Qwen-32B2026.06 | 91 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=Qwen-7B2026.06 | 91 | — | — | — | — | — | — | — | — | |
| JR1+Target model=Qwen-7B2026.06 | 88 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=Qwen-32B2026.06 | 87 | — | — | — | — | — | — | — | — | |
| JR1+Target model=Qwen-32B2026.06 | 87 | — | — | — | — | — | — | — | — | |
| GCG+Target model=Qwen-7B2026.06 | 87 | — | — | — | — | — | — | — | — | |
| GCG+Target model=Qwen-32B2026.06 | 84 | — | — | — | — | — | — | — | — | |
| IHOTarget model=LLaMA-8B2026.06 | 84 | — | — | — | — | — | — | — | — | |
| INP.Target model=Qwen-7B2026.06 | 82 | — | — | — | — | — | — | — | — | |
| JR1+Target model=LLaMA-8B2026.06 | 82 | — | — | — | — | — | — | — | — | |
| IHOTarget model=CB2026.06 | 82 | — | — | — | — | — | — | — | — | |
| IHOTarget model=Qwen-7B+D2026.06 | 80 | — | — | — | — | — | — | — | — | |
| BONTarget model=LLaMA-8B2026.06 | 79 | — | — | — | — | — | — | — | — | |
| IHOTarget model=CAT2026.06 | 79 | — | — | — | — | — | — | — | — | |
| INP.Target model=Qwen-32B2026.06 | 78 | — | — | — | — | — | — | — | — | |
| IHOTarget model=LAT2026.06 | 78 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=Qwen-7B2026.06 | 77 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=LLaMA-8B2026.06 | 77 | — | — | — | — | — | — | — | — | |
| IHOTarget model=CB+D2026.06 | 77 | — | — | — | — | — | — | — | — | |
| GCG+Target model=LLaMA-8B2026.06 | 76 | — | — | — | — | — | — | — | — | |
| INP.Target model=LLaMA-8B2026.06 | 75 | — | — | — | — | — | — | — | — | |
| BONTarget model=Qwen-7B2026.06 | 73 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=Qwen-32B2026.06 | 71 | — | — | — | — | — | — | — | — | |
| BONTarget model=Qwen-32B2026.06 | 71 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=Qwen-7B+D2026.06 | 71 | — | — | — | — | — | — | — | — | |
| JR1+Target model=CAT2026.06 | 70 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=CAT2026.06 | 67 | — | — | — | — | — | — | — | — | |
| JR1+Target model=Qwen-7B+D2026.06 | 66 | — | — | — | — | — | — | — | — | |
| INP.Target model=Qwen-7B+D2026.06 | 66 | — | — | — | — | — | — | — | — | |
| INP.Target model=CB2026.06 | 63 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=LAT2026.06 | 63 | — | — | — | — | — | — | — | — | |
| JR1+Target model=LAT2026.06 | 62 | — | — | — | — | — | — | — | — | |
| INP.Target model=LAT2026.06 | 61 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=CB2026.06 | 58 | — | — | — | — | — | — | — | — | |
| BONTarget model=Qwen-7B+D2026.06 | 57 | — | — | — | — | — | — | — | — | |
| INP.Target model=CB+D2026.06 | 55 | — | — | — | — | — | — | — | — | |
| INP.Target model=CAT2026.06 | 54 | — | — | — | — | — | — | — | — | |
| Ample+Target model=Qwen-7B2026.06 | 52 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=LLaMA-8B2026.06 | 49 | — | — | — | — | — | — | — | — | |
| JR1+Target model=CB2026.06 | 47 | — | — | — | — | — | — | — | — | |
| PAIR+Target model=CB+D2026.06 | 46 | — | — | — | — | — | — | — | — | |
| GCG+Target model=LAT2026.06 | 46 | — | — | — | — | — | — | — | — | |
| BONTarget model=CB2026.06 | 45 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=Qwen-7B+D2026.06 | 41 | — | — | — | — | — | — | — | — | |
| JR1+Target model=CB+D2026.06 | 38 | — | — | — | — | — | — | — | — | |
| BONTarget model=CB+D2026.06 | 37 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=CAT2026.06 | 35 | — | — | — | — | — | — | — | — | |
| Ample+Target model=Qwen-32B2026.06 | 31 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=LAT2026.06 | 31 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=CB2026.06 | 25 | — | — | — | — | — | — | — | — | |
| PAIRTarget model=CB+D2026.06 | 17 | — | — | — | — | — | — | — | — | |
| GCG+Target model=CB2026.06 | 14 | — | — | — | — | — | — | — | — | |
| Ample+Target model=CB2026.06 | 11 | — | — | — | — | — | — | — | — | |
| Ample+Target model=LLaMA-8B2026.06 | 8 | — | — | — | — | — | — | — | — | |
| Ample+Target model=Qwen-7B+D2026.06 | 6 | — | — | — | — | — | — | — | — | |
| GCG+Target model=CAT2026.06 | 4 | — | — | — | — | — | — | — | — | |
| Ample+Target model=CB+D2026.06 | 2 | — | — | — | — | — | — | — | — | |
| BONTarget model=LAT2026.06 | 2 | — | — | — | — | — | — | — | — | |
| BONTarget model=CAT2026.06 | 1 | — | — | — | — | — | — | — | — | |
| Ample+Target model=LAT2026.06 | 0 | — | — | — | — | — | — | — | — | |
| Ample+Target model=CAT2026.06 | 0 | — | — | — | — | — | — | — | — | |
| AmpleGCG+Target model=Qwen-2.5-32B2026.06 | — | — | 8 | — | — | — | — | — | — | |
| AmpleGCG+Target model=Qwen-2.5-7B2026.06 | — | — | 28 | — | — | — | — | — | — | |
| AmpleGCG+Target model=Qwen-2.5-7B+D2026.06 | — | — | 0 | — | — | — | — | — | — | |
| AmpleGCG+Target model=LLaMA-3-8B2026.06 | — | — | 2 | — | — | — | — | — | — | |
| AmpleGCG+Target model=CB2026.06 | — | — | 0 | — | — | — | — | — | — | |
| AmpleGCG+Target model=CB+D2026.06 | — | — | 0 | — | — | — | — | — | — | |
| AmpleGCG+Target model=LAT2026.06 | — | — | 0 | — | — | — | — | — | — | |
| AmpleGCG+Target model=CAT2026.06 | — | — | 0 | — | — | — | — | — | — | |
| BONTarget model=Qwen-2.5-32B2026.06 | — | — | — | — | — | 45 | — | — | — | |
| BONTarget model=Qwen-2.5-7B2026.06 | — | — | — | — | — | 50 | — | — | — | |
| BONTarget model=Qwen-2.5-7B+D2026.06 | — | — | — | — | — | 10 | — | — | — | |
| BONTarget model=LLaMA-3-8B2026.06 | — | — | — | — | — | 73 | — | — | — | |
| BONTarget model=CB2026.06 | — | — | — | — | — | 5 | — | — | — | |
| BONTarget model=CB+D2026.06 | — | — | — | — | — | 3 | — | — | — | |
| BONTarget model=LAT2026.06 | — | — | — | — | — | 0 | — | — | — | |
| BONTarget model=CAT2026.06 | — | — | — | — | — | 0 | — | — | — | |
| GCG+Target model=Qwen-2.5-32B2026.06 | — | 73 | — | — | — | — | — | — | — | |
| GCG+Target model=Qwen-2.5-7B2026.06 | — | 82 | — | — | — | — | — | — | — | |
| GCG+Target model=LLaMA-3-8B2026.06 | — | 68 | — | — | — | — | — | — | — | |
| GCG+Target model=CB2026.06 | — | 0 | — | — | — | — | — | — | — | |
| GCG+Target model=LAT2026.06 | — | 17 | — | — | — | — | — | — | — | |
| GCG+Target model=CAT2026.06 | — | 2 | — | — | — | — | — | — | — | |
| IHOTarget model=Qwen-2.5-32B2026.06 | — | — | — | — | — | — | — | — | 90 | |
| IHOTarget model=Qwen-2.5-7B2026.06 | — | — | — | — | — | — | — | — | 88 | |
| IHOTarget model=Qwen-2.5-7B+D2026.06 | — | — | — | — | — | — | — | — | 60 | |
| IHOTarget model=LLaMA-3-8B2026.06 | — | — | — | — | — | — | — | — | 77 | |
| IHOTarget model=CB2026.06 | — | — | — | — | — | — | — | — | 63 | |
| IHOTarget model=CB+D2026.06 | — | — | — | — | — | — | — | — | 43 | |
| IHOTarget model=LAT2026.06 | — | — | — | — | — | — | — | — | 58 | |
| IHOTarget model=CAT2026.06 | — | — | — | — | — | — | — | — | 65 | |
| INPAINTINGTarget model=Qwen-2.5-32B2026.06 | — | — | — | — | — | — | — | 70 | — | |
| INPAINTINGTarget model=Qwen-2.5-7B2026.06 | — | — | — | — | — | — | — | 77 | — | |
| INPAINTINGTarget model=Qwen-2.5-7B+D2026.06 | — | — | — | — | — | — | — | 37 | — | |
| INPAINTINGTarget model=LLaMA-3-8B2026.06 | — | — | — | — | — | — | — | 62 | — | |
| INPAINTINGTarget model=CB2026.06 | — | — | — | — | — | — | — | 37 | — | |
| INPAINTINGTarget model=CB+D2026.06 | — | — | — | — | — | — | — | 20 | — | |
| INPAINTINGTarget model=LAT2026.06 | — | — | — | — | — | — | — | 25 | — | |
| INPAINTINGTarget model=CAT2026.06 | — | — | — | — | — | — | — | 18 | — |