Work

FixGuard: Repairing Backdoored Models via Class-Wise Trigger Recovery and Unlearning

Year: 2025

Type: article

Source: IEEE Signal Processing Letters

DOI: 10.1109/lsp.2025.3572409

Authors: Linshan Hou, Zhongyun Hua, Wei Luo, Leo Yu Zhang

Institutions: Harbin Institute of Technology, Deakin University, Griffith University

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funder: National Natural Science Foundation of China

Award: 高维鲁棒混沌机理研究及其在生成式对抗网络中的应用

OpenAlex ID: W4410614277

FWCI: 0.408

Cites: 50

Cited by: 1

Related to: 10