Jailbreak Attack Robustness on Role-Play jailbreak attack
2,108DSR
TGA-7B
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2024.10 | 2,108 | |
2024.10 | 1,348 | |
2024.10 | 455 | |
2024.10 | 295 | |
2024.10 | 67 | |
2024.10 | 66 | |
2024.10 | 32 |
TGA-7B
| Method | Links | |
|---|---|---|
2024.10 | 2,108 | |
2024.10 | 1,348 | |
2024.10 | 455 | |
2024.10 | 295 | |
2024.10 | 67 | |
2024.10 | 66 | |
2024.10 | 32 |