most citedA Survey of Recent Backdoor Attacks and Defenses in Large Language Models

2 citations · 5 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2024★ 1 cited

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.…

cs.CL2024★ 2 cited

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…