Jailbreak Attack Robustness on Role-Play jailbreak attack
2,108DSRTGA-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| TGA-7Bparameters=7B2024.10 | 2,108 | |
| Unlearn-FigS2024.10 | 1,348 | |
| Qwen-VL-chatvariant=chat2024.10 | 455 | |
| InstructBlip2024.10 | 295 | |
| LLaVA-v1.5version=v1.52024.10 | 67 | |
| LLaVA-v1.6version=v1.62024.10 | 66 | |
| BLIP-22024.10 | 32 |