Jailbreak Robustness on AutoRAN
0Harmfulness RateRealSafe-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| RealSafe-R1Model=R1-Qwen-14B2025.08 | 0 | |
| SafeKeyModel=R1-Qwen-14B2025.08 | 0 | |
| ThinkingIModel=R1-Qwen-14B2025.08 | 0 | |
| SAFEPATH-ZSModel=R1-Qwen-14B2025.08 | 0 | |
| ReasoningGuardModel=R1-Qwen-14B2025.08 | 0 | |
| No DefenseModel=R1-Qwen-32B2025.08 | 0 | |
| RealSafe-R1Model=R1-Qwen-32B2025.08 | 0 | |
| SAFEPATH-ZSModel=R1-Qwen-32B2025.08 | 0 | |
| ReasoningGuardModel=R1-Qwen-32B2025.08 | 0 | |
| No DefenseModel=R1-Qwen-14B2025.08 | 2 | |
| Self-ReminderModel=R1-Qwen-14B2025.08 | 2 | |
| SmoothLLMModel=R1-Qwen-14B2025.08 | 2 | |
| ParaphraseModel=R1-Qwen-32B2025.08 | 2 | |
| Self-ReminderModel=R1-Qwen-32B2025.08 | 4 | |
| SmoothLLMModel=R1-Qwen-32B2025.08 | 4 | |
| ParaphraseModel=R1-Qwen-14B2025.08 | 6 | |
| ThinkingIModel=R1-Qwen-32B2025.08 | 6 |