Papers with JPU
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are vulnerable to diverse jailbreak attacks despite extensive safety alignment . |
| Approach: | They propose a method to rectify dynamic jailbreak paths towards safety anchors by dynamically mining on-policy adversarial samples to expose vulnerabilities and identify jailbreak path. |
| Outcome: | The proposed model significantly improves jailbreak resistance against dynamic attacks while maintaining its utility. |