Jailbreak Attack on Llama2-7b five finetuned variants
0Average ASR
PIF
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.12 | 0 | |
2025.12 | 0 | |
2025.12 | 0 | |
2025.12 | 1.8 | |
2025.12 | 3.2 | |
2025.12 | 6.2 | |
2025.12 | 15.8 | |
2025.12 | 16 | |
2025.12 | 20.4 | |
2025.12 | 24.8 | |
2025.12 | 25.6 | |
2025.12 | 28 | |
2025.12 | 33.2 | |
2025.12 | 40.2 | |
2025.12 | 47.4 | |
2025.12 | 62.6 |