Year: 2024
Type: preprint
Abstract: Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can compromise the robustness of LLMs and amplify harmful behaviors-an attack commonly referred to as jailbreaking. To address this challenge, we propose an adaptive data curation approach allowing any text to be curated to enhance its effectiveness in counteracting harmful samples during customization. To avoid the need for additional defensive modules, we further introduce a comprehensive mitigation framework spanning the lifecycle of the customization process: before customization to immunize LLMs against future jailbreak attempts, during customization to neutralize risks, and after customization to restore compromised models. Experimental results demonstrate a significant reduction in jailbreaking effects, achieving up to a 100% success rate in generating safe responses. By combining adaptive data curation with lifecycle-based mitigation strategies, this work represents a solid step forward in mitigating jailbreaking risks and ensuring the secure adaptation of LLMs.
Source: arXiv (Cornell University)
Authors: Liu, Xiaoqun, Liang, Jiacheng, Tang, Luoxi, Ye, Muchao, Ma, Weicheng, Xi, Zhaohan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4403885204