Jailbreak Attack on HarmBench example-based Llama3 RR (8B)
0Attack Success RateAdaptive Attack
Evaluation results
| Method | Links | |
|---|---|---|
| Adaptive AttackHuman Readable=false, Zero-shot=true2025.12 | 0 | |
| GCG AttackHuman Readable=false, Zero-shot=true2025.12 | 2 | |
| PAIR AttackHuman Readable=true, Zero-shot=true2025.12 | 22 | |
| AutoDAN TurboHuman Readable=true, Zero-shot=true2025.12 | 26 | |
| Adversarial ReasoningHuman Readable=true, Zero-shot=true2025.12 | 44 | |
| Jailbreak-ZeroHuman Readable=true, Zero-shot=true2025.12 | 83 |