【Author】
Mothukuri, Viraaji; Parizi, Reza M.; Pouriyeh, Seyedamin; Dehghantanha, Ali; Choo, Kim-Kwang Raymond
【Source】IEEE SYSTEMS JOURNAL
【Abstract】Federated learning (FL) enables collaborative training of machine learning (ML) models while preserving user data privacy. Existing FL approaches can potentially facilitate collaborative ML, but ensuring secure trading/sharing of training data is challenging in practice, particularly in the presence of adversarial FL clients. The ongoing security concerns around FL and strict laws on personally identifiable information necessitate the design of a robust and trusted FL framework, for example, using blockchain. Existing blockchain-based solutions are generally not of industrial strength, where limitations include scalability and lack of engagement by participating clients. In this article, blockchain-in-the-loop FL is our proposed approach of intertwining classic FL and Hyperledger Fabric with a gamification component. Our proposed approach is a fusion of secure application integrated to seal and sign-off asynchronous and synchronous collaborative tasks of FL. The enterprise-level blockchain network provides an immutable ledger that can be leveraged at different FL layers to ensure auditable tracing and level-up security in industrial settings. We evaluate our proposed approach with three different datasets to demonstrate the security enhancements that improve the FL process, resulting in a more accurate global ML model to converge with the possible best performance.
【Keywords】Blockchains; Training; Data models; Computational modeling; Task analysis; Security; Organizations; Blockchain; decentralized artificial intelligence; federated learning (FL); hyperledger fabric (HLF); privacy-preserving machine learning (ML); security
【标题】FabricFL：可信去中心化系统的区块链在环联邦学习
【摘要】联邦学习 (FL) 支持机器学习 (ML) 模型的协作训练，同时保护用户数据隐私。现有的 FL 方法可能会促进协作式 ML，但确保训练数据的安全交易/共享在实践中具有挑战性，特别是在存在对抗性 FL 客户的情况下。围绕 FL 的持续安全问题和关于个人身份信息的严格法律要求设计一个强大且受信任的 FL 框架，例如使用区块链。现有的基于区块链的解决方案通常不具备工业实力，其局限性包括可扩展性和参与客户缺乏参与。在本文中，blockchain-in-the-loop FL 是我们提出的将经典 FL 和 Hyperledger Fabric 与游戏化组件交织在一起的方法。我们提出的方法是融合安全应用程序，集成到密封和签署 FL 的异步和同步协作任务。企业级区块链网络提供了一个不可变的账本，可以在不同的 FL 层使用，以确保工业环境中的可审计跟踪和升级安全性。我们使用三个不同的数据集评估我们提出的方法，以展示改进 FL 过程的安全增强功能，从而产生更准确的全局 ML 模型，以达到可能的最佳性能。
【关键词】区块链；训练;数据模型；计算建模；任务分析；安全;组织；区块链；去中心化人工智能；联邦学习（FL）；超级账本结构（HLF）；保护隐私的机器学习 (ML)；安全
【文献类型】Article; Early Access
评论