DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing

ACL ARR 2025 February Submission4920 Authors

Abstract: Large Language Models (LLMs) are widely applied in decision making, but their deployment is threatened by jailbreak attacks, where adversarial users manipulate model behavior to bypass safety measures. Existing defense mechanisms, such as safety fine-tuning and model editing, either require extensive parameter modifications or lack precision, leading to performance degradation on general tasks, which is unsuitable to post-deployment safety alignment. To address these challenges, we propose *DELMAN* (**D**ynamic **E**diting for **L**L**M**s J**A**ilbreak Defe**N**se), a novel approach leveraging direct model editing for precise, dynamic protection against jailbreak attacks. *DELMAN* directly updates a minimal set of relevant parameters to neutralize harmful behaviors while preserving the model's utility. To avoid triggering a safe response in benign context, we incorporate KL-divergence regularization to ensure the updated model remains consistent with the original model when processing benign queries. Experimental results demonstrate that *DELMAN* outperforms baseline methods in mitigating jailbreak attacks while preserving the model’s utility, and adapts seamlessly to new attack instances, providing a practical and efficient solution for post-deployment model protection.

Paper Type: Long

Research Area: Language Modeling

Research Area Keywords: security and privacy, red teaming, robustness

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 4920