4 papers
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation
Shuai Zhao, Xiaobao Wu, Cong-Duy Nguyen +4
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.…
A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
Shuai Zhao, Meihuizi Jia, Zhongliang Guo +7
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, part…
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Shuai Zhao, Leilei Gan, Luu Anh Tuan +4
Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to language models have been proposed and successfully implemented. However, this raises the que…
Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning
Shuai Zhao, Meihuizi Jia, Luu Anh Tuan +2
In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite…