LLM Jailbreaking on JBB-Behaviors Scenario J2
0.691HypervolumeEvoJail
Evaluation Results
| Method | Links | |
|---|---|---|
| EvoJailTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.691 | |
| CodeAttackTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.589 | |
| EvoJailTarget Model=gpt-4.1-Nano2026.03 | 0.589 | |
| CodeAttackTarget Model=gpt-4.1-Nano2026.03 | 0.553 | |
| ReNeLLMTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.456 | |
| CodeChameleonTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.432 | |
| EvoJailTarget Model=Llama-2-7b-chat-hf2026.03 | 0.419 | |
| JailbrokenTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.418 | |
| FlipAttackTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.373 | |
| CodeChameleonTarget Model=gpt-4.1-Nano2026.03 | 0.256 | |
| JailbrokenTarget Model=Llama-2-7b-chat-hf2026.03 | 0.241 | |
| CodeChameleonTarget Model=Llama-2-7b-chat-hf2026.03 | 0.195 | |
| ReNeLLMTarget Model=Llama-2-7b-chat-hf2026.03 | 0.144 | |
| CipherTarget Model=Llama-3.1-8B-Instruct2026.03 | 0.099 | |
| FlipAttackTarget Model=gpt-4.1-Nano2026.03 | 0.062 | |
| ReNeLLMTarget Model=gpt-4.1-Nano2026.03 | 0.056 | |
| CodeAttackTarget Model=Llama-2-7b-chat-hf2026.03 | 0.049 | |
| FlipAttackTarget Model=Llama-2-7b-chat-hf2026.03 | 0.046 | |
| CipherTarget Model=Llama-2-7b-chat-hf2026.03 | 0 | |
| JailbrokenTarget Model=gpt-4.1-Nano2026.03 | 0 | |
| CipherTarget Model=gpt-4.1-Nano2026.03 | 0 |