Jailbreak Attack on GPT-J unseen instances
0.61HypervolumeCodeAttack
Evaluation Results
| Method | Links | |
|---|---|---|
| CodeAttackEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0.61 | |
| EvoJailEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0.549 | |
| CodeChameleonEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0.419 | |
| FlipAttackEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0.114 | |
| ReNeLLMEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0.053 | |
| JailbrokenEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0 | |
| CipherEvaluation Level=ensemble level, Instance Type=unseen instances2026.03 | 0 |