| JBB-Behaviors | SAGE | ASR0 | | 101 | 4d ago |
| DeepInception | | Harmful Score1 | | 58 | 4d ago |
| AutoDAN | SafeDecoding | ASR0 | | 51 | 4d ago |
| AdvBench | | ASR (Overall)0 | | 49 | 4d ago |
| HarmBench and AdvBench (test) | | GCG Score91.2 | | 44 | 4d ago |
| Behaviours (test) | | ASR0.9 | | 44 | 4d ago |
| ReNeLLM | IA | Harmful Score1 | | 42 | 4d ago |
| PAIR | SAGE | Harmful Score1 | | 37 | 4d ago |
| GCG | | Harmful Score1 | | 37 | 4d ago |
| Wild Jailbreak | Ours | ASR0.5 | | 36 | 4d ago |
| AdvBench PAIR attack | SmoothLLM | DSR98 | | 35 | 4d ago |
| Jailbreak Attack Benchmarks (GPTFuzz, TAP, GCG, AutoDAN, Template) | | GPTFuzz ASR24.98 | | 24 | 4d ago |
| JailbreakBench and AdvBench | Certified Semantic Smoothing | ASR0.1 | | 21 | 4d ago |
| Aggregate Benchmarks | SAGE | Harmful Score1.06 | | 21 | 4d ago |
| GPTFuzzer | Self-Examination | Harmful Score1 | | 21 | 4d ago |
| ReNeLLM & DeepInception Average | IA | Harmful Score1 | | 21 | 4d ago |
| Template | | Harmful Score1.02 | | 16 | 4d ago |
| SAP30 | | Harmful Score1 | | 16 | 4d ago |
| HEX-PHI | | Harmful Score1.74 | | 16 | 4d ago |
| AdvBench (test) | | Harmful Score1 | | 16 | 4d ago |
| AdvBench AutoDAN attack | SmoothLLM | DSR100 | | 15 | 4d ago |
| AdvBench GCG attack | SmoothLLM | DSR100 | | 15 | 4d ago |
| MIX-JAIL AdvB-Short | JPU | ASR4.44 | | 14 | 4d ago |
| Decoding MaliciousInstruct | JPU | ASR1 | | 14 | 4d ago |
| AutoDAN AdvE | CKU | ASR9.83 | | 14 | 4d ago |