Jailbreak Defense on LLaMA2-7B Adaptive PAIR attack
0Attack Success Rate (ASR)Vanilla
Evaluation Results
| Method | Links | |
|---|---|---|
| VanillaTarget Model=LLaMA2-7B, Attack=Adaptive PAIR2026.05 | 0 | |
| Perplexity FilterTarget Model=LLaMA2-7B, Attack=Adaptive PAIR2026.05 | 0 | |
| Erase-and-CheckTarget Model=LLaMA2-7B, Attack=Adaptive PAIR2026.05 | 0 | |
| Embedding Disruption MethodTarget Model=LLaMA2-7B, Attack=Adaptive PAIR2026.05 | 0 | |
| SmoothLLMTarget Model=LLaMA2-7B, Attack=Adaptive PAIR2026.05 | 2 | |
| RESTATarget Model=LLaMA2-7B, Attack=Adaptive PAIR2026.05 | 2 |