郑州大学学报（理学版）2025，Vol.57Issue(4)：23-29,7.DOI:10.13705/j.issn.1671-6841.2024036
基于联盟链的隐私保护联邦学习框架
A Privacy-preserving Federated Learning Framework Based on Consortium Chain
摘要
Abstract
Aiming at the shortcomings of existing federated learning models in privacy protection and poi-soning attack defense,a privacy-preserving federated learning framework based on consortium chain was proposed.Firstly,the framework employed homomorphic encryption techniques and Laplacian noise to ensure data privacy,effectively preserving the confidentiality of data from various parties during model training.Secondly,through the consensus protocol of the consortium chain and a model aggregation algo-rithm,distinct gradient aggregation weights were assigned to different participants,mitigating the impact of malicious parties on model aggregation and enhancing the robustness of the model.The experimental results conducted on the MNIST and Fashion-MNIST datasets demonstrated that even with a malicious participant ratio up to 40％,the proposed framework could still maintain high model accuracy with label reversal attack and backdoor attack.关键词
联邦学习/隐私保护/投毒攻击/联盟链/模型聚合Key words
federated learning/privacy protection/poisoning attack/consortium chain/model aggrega-tion分类
计算机与自动化引用本文复制引用
韦超,杨闻韶,刘炜..基于联盟链的隐私保护联邦学习框架[J].郑州大学学报（理学版）,2025,57(4):23-29,7.基金项目
燕山大学博士基金项目(8190047) （8190047）
