A unified optimization framework for backdoor attacks in large language models

Information Fusion 2026

View at publisher

Authors: Yihan Shi, Wenlong Zheng, He Xu, Xu An Wang, Ruchuan Wang

DOI: 10.1016/j.inffus.2026.104221

Cited by: 0

References: 10

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Topic Modeling Privacy-Preserving Technologies in Data

References 10