计算机应用研究2024，Vol.41Issue(1)：26-31,6.DOI:10.19734/j.issn.1001-3695.2023.05.0208
区块链赋能多边缘安全联邦学习模型
Blockchain-empowered multiple edge secure federated learning model
摘要
Abstract
Federated learning is a revolutionary deep learning model,and it enables users to train the global model coopera-tively without exposing their private data.However,malicious behaviors of some clients can lead to the risk of single point of failure and privacy disclosure,which pose a serious threat to the security of federated learning.In response to the above is-sues,based on the existing research,this paper proposed a blockchain empowered multi edge federated learning model.First-ly,this paper proposed to use blockchain instead of central server to enhance the stability and reliability of model training process.Secondly,this paper proposed a consensus mechanism based on edge computing to achieve a more efficient consensus process.In addition,incorporating reputation assessment into the federated learning training process,it could transparently measure the contribution value of each participant and standardize the behavior of work nodes.Finally,comparative experi-ments show that the scheme can maintain high accuracy in the malicious environment,and can resist higher malicious ratio compared with the traditional federated learning algorithms.关键词
人工智能/联邦学习/区块链/边缘计算/共识机制Key words
artificial intelligence/federated learning/blockchain/edge computing/consensus mechanism分类
信息技术与安全科学引用本文复制引用
姜晓宇,顾瑞春,张欢..区块链赋能多边缘安全联邦学习模型[J].计算机应用研究,2024,41(1):26-31,6.基金项目
内蒙古自然科学基金资助项目(2021LHMS06003) （2021LHMS06003）
内蒙古高校基本科研业务费资助项目(114) （114）
