通信学报2026，Vol.47Issue(8)：78-93,16.DOI:10.11959/j.issn.1000-436x.TXXB260183
Fed-DCR:基于双域协同检测的联邦学习后门防御方案
Fed-DCR:a backdoor defense scheme for federated learning based on dual-domain synergistic detection
摘要
Abstract
Federated learning has been shown to be vulnerable to backdoor attacks,while existing defense methods mainly rely on single statistical features in the parameter space.Under non-IID conditions,the overlap between benign and mali-cious update features often leads to degraded detection performance,while dedicated defense schemes for low-rank fine-tuning scenarios remain underexplored.To address these issues,Fed-DCR,a backdoor defense scheme for federated learn-ing based on dual-domain synergistic detection,was proposed.In the frequency domain,the discrete cosine transform(DCT)was used to decouple client updates,while semantic alignment and spectral density clustering were introduced to improve the separability between benign and malicious updates.In the parameter domain,low-rank adaptation(LoRA)spectral consistency detection was employed to identify anomalous deviations in the low-rank subspace,while causal prob-ing was integrated to actively expose hidden backdoors.Experimental results show that Fed-DCR effectively reduces the success rates of multiple backdoor attacks on both the CIFAR-10 vision task and the Llama-2-7B-based federated LoRA fine-tuning task.Fed-DCR provides a favorable balance between backdoor mitigation and main-task performance across most experimental settings.关键词
联邦学习安全/后门防御/双域协同检测/鲁棒聚合Key words
federated learning security/backdoor defense/dual-domain synergistic detection/robust aggregation分类
信息技术与安全科学引用本文复制引用
康杰,杜瑞忠,梁晓艳,张晓羽,石朋亮,王劭晴..Fed-DCR:基于双域协同检测的联邦学习后门防御方案[J].通信学报,2026,47(8):78-93,16.基金项目
京津冀自然科学基金合作专项资助项目(No.25JJJJC0037) （No.25JJJJC0037）
河北省教育厅科学研究资助项目(No.QN2024200) The Beijing-Tianjin-Hebei Natural Science Foundation Cooperation Project(No.25JJJJC0037),The Science Re-search Project of Hebei Education Department(No.QN2024200) （No.QN2024200）
