harmful requests and jailbreak prompts
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Attack Success Rate | 20,000 harmful requests and 20,000 jailbreak prompts (test) | Attack Success Rate (ASR)80.2 | 18 |
Showing 1 of 1 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Attack Success Rate | 20,000 harmful requests and 20,000 jailbreak prompts (test) | Attack Success Rate (ASR)80.2 | 18 |