Jailbreak Defense on Emoji Attack DrAttack
0ASRSelfGrader
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SelfGraderTarget LLM=LLama-3-8B Instruct2026.04 | 0 | 0 | |
| SelfDefendvariant=Direct, Target LLM=LLama-3-8B Instruct2026.04 | 9 | 44 | |
| Llama Guardvariant=Pre, Target LLM=LLama-3-8B Instruct2026.04 | 16 | 99 |