Jailbreak Attack on AdvBench Llama3.1-405B 1.0 (test)
0ASRGCG
Evaluation Results
| Method | Links | |
|---|---|---|
| GCGAttack Type=Automated, Evaluator=GPT-42025.12 | 0 | |
| MACAttack Type=Automated, Evaluator=GPT-42025.12 | 0 | |
| Base64Attack Type=Automated, Evaluator=GPT-42025.12 | 0 | |
| GPTFuzzerAttack Type=Automated, Evaluator=GPT-42025.12 | 0 | |
| DRAAttack Type=Manual, Evaluator=GPT-42025.12 | 0 | |
| PromptAttackAttack Type=Manual, Evaluator=GPT-42025.12 | 0 | |
| SelfCipherAttack Type=Manual, Evaluator=GPT-42025.12 | 0 | |
| ArtPromoptAttack Type=Manual, Evaluator=GPT-42025.12 | 38 | |
| CodeChameleonAttack Type=Manual, Evaluator=GPT-42025.12 | 58 | |
| COLD-AttackAttack Type=Automated, Evaluator=GPT-42025.12 | 77 | |
| TAPAttack Type=Automated, Evaluator=GPT-42025.12 | 77 | |
| ReNeLLMAttack Type=Manual, Evaluator=GPT-42025.12 | 154 | |
| DeepInceptionAttack Type=Manual, Evaluator=GPT-42025.12 | 192 | |
| PAIRAttack Type=Automated, Evaluator=GPT-42025.12 | 212 | |
| AutoDANAttack Type=Automated, Evaluator=GPT-42025.12 | 327 | |
| EquaCodeEvaluator=GPT-42025.12 | 1,788 | |
| FlipattackAttack Type=Manual, Evaluator=GPT-42025.12 | 2,750 |