Jailbreak Attack Evaluation on DeepIn
68ASRICD
Evaluation Results
| Method | Links | |
|---|---|---|
| ICDBase LLM=Vicuna2025.08 | 68 | |
| No DefenseBase LLM=Vicuna2025.08 | 56 | |
| Self-ExaminationBase LLM=Vicuna2025.08 | 44 | |
| Self-ReminderBase LLM=Vicuna2025.08 | 40 | |
| No DefenseBase LLM=ChatGPT2025.08 | 20 | |
| Self-ReminderBase LLM=ChatGPT2025.08 | 16 | |
| Self-ExaminationBase LLM=ChatGPT2025.08 | 4 | |
| Context FilteringBase LLM=Vicuna2025.08 | 2 | |
| No DefenseBase LLM=Llama22025.08 | 2 | |
| Intention AnalysisBase LLM=Vicuna2025.08 | 0 | |
| Safe DecodingBase LLM=Vicuna2025.08 | 0 | |
| Self-ReminderBase LLM=Llama22025.08 | 0 | |
| ICDBase LLM=Llama22025.08 | 0 | |
| Self-ExaminationBase LLM=Llama22025.08 | 0 | |
| Intention AnalysisBase LLM=Llama22025.08 | 0 | |
| Safe DecodingBase LLM=Llama22025.08 | 0 | |
| Context FilteringBase LLM=Llama22025.08 | 0 | |
| ICDBase LLM=ChatGPT2025.08 | 0 | |
| Intention AnalysisBase LLM=ChatGPT2025.08 | 0 | |
| Context FilteringBase LLM=ChatGPT2025.08 | 0 |