AAAI 2026technical0 citations
CL-Guard: Defending DNNs Against Backdoors via Fine-Grained Neuron Analysis and Collaborative Dual-Network Learning
Jie Xiao, Yuhao Huang, Yanjiao Gao, Aizhu Liu, Zhezhao Yang, Xinyue Yu, Qianwei Zhou, Fan Terry Zhang
Abstract
Backdoor attacks on deep neural networks (DNNs) have garnered significant attention, particularly in edge computing applications. Given the complexity and opacity of DNNs, defending against backdoor attacks remains a formidable challenge. To address this, we propose CL-Guard, a dual-network-based defense framework designed to effectively eliminate potential backdoors in models. First, it leverages an inter-layer backpropagation algorithm to quantify each neuron
BibTeX
@inproceedings{aaai2026_clguarddefending,
title = {CL-Guard: Defending DNNs Against Backdoors via Fine-Grained Neuron Analysis and Collaborative Dual-Network Learning},
author = {Jie Xiao and Yuhao Huang and Yanjiao Gao and Aizhu Liu and Zhezhao Yang and Xinyue Yu and Qianwei Zhou and Fan Terry Zhang},
booktitle = {AAAI 2026},
year = {2026}
}