AI RESEARCH
Activation-Guided Local Editing for Jailbreaking Attacks
arXiv CS.AI
•
ArXi:2508.00555v2 Announce Type: replace-cross Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or unreadable inputs and exhibit poor transferability, while prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity. We propose a concise and effective two-stage framework that combines the advantages of these approaches.