Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
Shuai Zhao, Xiaobao Wu, Cong-Duy T Nguyen, Yanhao Jia, Meihuizi Jia, Yichao Feng, Anh Tuan Luu
Nanyang Technological University Northwest Normal University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models (LLMs) and downstream tasks.However, PEFT has been proven vulnerable to malicious attacks.Research indicates that poisoned LLMs, even after PEFT, retain the capability to activate internalized backdoors when input samples contain predefined triggers.In this paper, we introduce a novel weak-to-strong unlearning algorithm to defend against backdoor attacks based on feature alignment knowledge distillation, named W2SDefense.Specifically, we first train a small-scale language model through full-parameter fine-tuning to serve as the clean teacher model.Then, this teacher model guides the large-scale poisoned student model in unlearning the backdoor, leveraging PEFT.Theoretical analysis suggests that W2SDefense has the potential to enhance the student model's ability to unlearn backdoor features, preventing the activation of the backdoor.We conduct comprehensive experiments on three state-ofthe-art large language models and several different backdoor attack algorithms.Our empirical results demonstrate the outstanding performance of W2SDefense in defending against backdoor attacks without compromising model performance 1 .
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAdversarial Robustness in Machine Learning
Privacy-Preserving Technologies in Data · Security and Verification in Computing