| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Jailbreak Defense | GCG | ASR0 | 91 | |
| Jailbreak Detection | GCG | Accuracy99 | 30 | |
| Jailbreak Attack | GCG | ASR96 | 27 | |
| Jailbreak Attack Defense | GCG | ASR0 | 24 | |
| Adversarial Robustness | GCG | GCG Rate0.13 | 21 | |
| Adversarial Attack Defense | GCG Individual | BAR100 | 18 | |
| Abnormal Behavior Detection | GCG (test) | Accuracy100 | 17 | |
| Jailbreak Detection | GCG | ASR13 | 15 | |
| Jailbreak Defense | GCG | ASR0 | 13 | |
| Interleaved text-mask generation | GCG (test) | METEOR17.4 | 10 | |
| Interleaved text-mask generation | GCG (val) | METEOR17.7 | 10 | |
| Text-only Jailbreak Attack Defense | GCG attack (test) | ASR8.24 | 9 | |
| Jailbreak Mitigation | GCG | GCG ASR1 | 4 | |
| Jailbreak Defense | GCG | LlamaGuard Score100 | 4 | |
| Prompt Injection | GCG Clean | ASR37.02 | 4 | |
| Jailbreak Resistance | GCG | Refusal Rate96.98 | 3 | |
| Grounded Conversation Generation | GCG (test) | mIoU62.34 | 3 |