Jailbreak Attack on AdvBench GPT-4-turbo 1.0 (test)
9,846ASREquaCode
Evaluation Results
| Method | Links | |
|---|---|---|
| EquaCodeEvaluator=GPT-42025.12 | 9,846 | |
| FlipattackAttack Type=Manual, Evaluator=GPT-42025.12 | 9,404 | |
| CodeChameleonAttack Type=Manual, Evaluator=GPT-42025.12 | 9,264 | |
| DRAAttack Type=Manual, Evaluator=GPT-42025.12 | 9,192 | |
| ReNeLLMAttack Type=Manual, Evaluator=GPT-42025.12 | 8,385 | |
| GPTFuzzerAttack Type=Automated, Evaluator=GPT-42025.12 | 5,135 | |
| TAPAttack Type=Automated, Evaluator=GPT-42025.12 | 3,681 | |
| AutoDANAttack Type=Automated, Evaluator=GPT-42025.12 | 3,192 | |
| PAIRAttack Type=Automated, Evaluator=GPT-42025.12 | 2,396 | |
| DeepInceptionAttack Type=Manual, Evaluator=GPT-42025.12 | 583 | |
| ArtPromoptAttack Type=Manual, Evaluator=GPT-42025.12 | 192 | |
| PromptAttackAttack Type=Manual, Evaluator=GPT-42025.12 | 96 | |
| GCGAttack Type=Automated, Evaluator=GPT-42025.12 | 38 | |
| MACAttack Type=Automated, Evaluator=GPT-42025.12 | 19 | |
| COLD-AttackAttack Type=Automated, Evaluator=GPT-42025.12 | 19 | |
| Base64Attack Type=Automated, Evaluator=GPT-42025.12 | 19 | |
| SelfCipherAttack Type=Manual, Evaluator=GPT-42025.12 | 0 |