基于区块链的隐私保护去中心化联邦学习模型  

Privacy-Preserving and Decentralized Federated Learning Model Based on the Blockchain

作　　者：周炜 王超 徐剑[3] 胡克勇 王金龙 Zhou Wei;Wang Chao;Xu Jian;Hu Keyong;Wang Jinlong(School of Information and Control Engineering,Qingdao University of Technology,Qingdao,Shandong 266520;National Key Laboratory of Mass Customization System and Technology(Haier Group Corporation),Qingdao,Shandong 266100;Software College,Northeastern University,Shenyang 110169)

机构地区：[1]青岛理工大学信息与控制工程学院,山东青岛266520 [2]大规模个性化定制系统与技术全国重点实验室(海尔集团公司),山东青岛266100 [3]东北大学软件学院,沈阳110169

出　　处：《计算机研究与发展》2022年第11期2423-2436,共14页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(61502262,61872069,61902205)。

摘　　要：传统的联邦学习依赖一个中央服务器,模型训练过程易受单点故障和节点恶意攻击的影响,明文传递的中间参数也可能被用来推断出数据中的隐私信息.提出了一种基于区块链的去中心化、安全、公平的联邦学习模型,利用同态加密技术保护协同训练方的中间参数隐私,通过选举的联邦学习委员会进行模型聚合和协同解密.解密过程通过秘密共享方案实现安全的密钥管理,利用双线性映射累加器为秘密份额提供正确性验证.引入信誉值作为评估参与方可靠性的指标,利用主观逻辑模型实现不信任增强的信誉计算作为联邦学习委员会的选举依据,信誉值作为激励机制的参考还可以保障参与公平性.模型信息和信誉值通过区块链实现数据的防篡改和不可抵赖.实验表明,模型在训练准确率相比中心化学习模型略有损失的情况下,能够保障在多方协作的环境下以去中心化的方式训练模型,有效实现了各参与方的隐私保护.Traditional federated learning relies on a central server,and the training process is vulnerable to single point of failure and malicious attacks from nodes,and intermediate parameters passed in plaintext may be exploited to infer the private information in data.A decentralized,secure,and fair federated learning model based on the blockchain is proposed,using homomorphic encryption technology to protect the privacy of the intermediate parameters of the collaborative training parties.Model aggregation and collaborative decryption are carried out through the elected federated learning committee.The decryption process achieves secure key management through a secret sharing scheme,using bilinear-map accumulator to provide verification of correctness for the secret share.The model also introduces reputation as an indicator to evaluate the reliability of the participants,and uses the subjective logic model to realize disbelief enhanced reputation calculation as the basis for the election of the federated learning committee.The reputation value can be used as a reference for the incentive mechanism to ensure fairness.Model information and the reputation value realize data tamper-proof and non-repudiation through the blockchain.Experiments show that in the condition of the training,accuracy is slightly lower than that of the centralized learning model,and model can guarantee that it can be trained in a decentralized manner in multi-party collaborative environment,and implement data privacy protection for all participants.

关 键 词：区块链 联邦学习 隐私保护 同态加密 双线性映射累加器 信誉 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]