Jailbreak Attack Evaluation on ReNe
0ASRIntention Analysis
Evaluation results
| Method | Links | |
|---|---|---|
| Intention AnalysisBase LLM=Vicuna2025.08 | 0 | |
| No DefenseBase LLM=Llama22025.08 | 0 | |
| Self-ExaminationBase LLM=ChatGPT2025.08 | 0 | |
| Intention AnalysisBase LLM=ChatGPT2025.08 | 0 | |
| Context FilteringBase LLM=Vicuna2025.08 | 8 | |
| Context FilteringBase LLM=ChatGPT2025.08 | 12 | |
| Self-ExaminationBase LLM=Vicuna2025.08 | 18 | |
| No DefenseBase LLM=Vicuna2025.08 | 26 | |
| Self-ReminderBase LLM=ChatGPT2025.08 | 26 | |
| Self-ReminderBase LLM=Vicuna2025.08 | 30 | |
| Safe DecodingBase LLM=Vicuna2025.08 | 30 | |
| ICDBase LLM=Vicuna2025.08 | 32 | |
| No DefenseBase LLM=ChatGPT2025.08 | 32 | |
| ICDBase LLM=ChatGPT2025.08 | 32 |