Attacks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Jailbreak Detection | Average of six attacks | Avg Success Rate0 | 38 | |
| Adversarial Attack Defense | Held-out attacks (test) | ASR (Multi-turn Manip.)7.8 | 2 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Jailbreak Detection | Average of six attacks | Avg Success Rate0 | 38 | |
| Adversarial Attack Defense | Held-out attacks (test) | ASR (Multi-turn Manip.)7.8 | 2 |