Adversarial Jailbreak Attacks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Jailbreak Defense | Adversarial Jailbreak Attacks Cipher, Instructional Constraint, Prefix Injection, Psychological Coercion (Alternative) | Safety Score (Cipher)100 | 5 |
Showing 1 of 1 rows