Prompt Injection Attack Robustness on WalledEval-Instruct 2024 (test)
50Attack Success PercentageHypnotism
Evaluation results
| Method | Links | ||
|---|---|---|---|
| HypnotismAttack Method=Hypnotism, Model Group=Open-source LLMs (Mean)2025.05 | 50 | 40 | |
| Ignore PrefixAttack Method=Ignore Prefix, Model Group=Open-source LLMs (Mean)2025.05 | 56.4 | 36 | |
| Role-playing CoTAttack Method=Role-playing CoT, Model Group=Open-source LLMs (Mean)2025.05 | 62.3 | 52.6 |