[论文解读] Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

Yang Zhao, Jun Zhao+6 more|arXiv (Cornell University)|Jun 26, 2019

Privacy-Preserving Technologies in Data参考文献 64被引用 53

一句话总结

提出一个基于区块链的面向物联网的众包联邦学习框架，使用差分隐私、IPFS 离链存储，以及基于声誉的激励系统，并以基于 Algorand 的区块链实现可审计性与安全性。

ABSTRACT

Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a smart home system. To help manufacturers develop a smart home system, we design a federated learning (FL) system leveraging the reputation mechanism to assist home appliance manufacturers to train a machine learning model based on customers' data. Then, manufacturers can predict customers' requirements and consumption behaviors in the future. The working flow of the system includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL system. Since records on the blockchain are untampered, malicious customers or manufacturers' activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers' privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

研究动机与目标

• 设计一个分层式众包FL系统，帮助家用电器制造商提升服务并预测消费者行为。
• 通过对提取的特征应用差分隐私以及引入一种新的归一化技术，为参与者提供隐私保护。
• 利用区块链对模型更新进行审计，防止篡改，并实现对贡献的可追溯性。
• 引入基于声誉和 Multi-KRUM 的激励机制，以奖励可靠的参与者并遏制中毒攻击。

提出的方法

• 将模型训练拆分为移动端特征提取并加入 epsilon-DP 噪声，然后在 MEC 服务器上训练全连接层。
• 使用 IPFS 进行链下存储，并在区块链上记录模型哈希以应对大型模型大小。
• 使用基于 Algorand PoS/BFT 共识的联盟区块链来管理模型提交、通过 Multi-KRUM 进行验证，以及用于全球模型聚合的领导者选举。
• 基于声誉的激励机制将 Multi-KRUM 与 VRF 选择的验证者结合起来，以计算参与者声誉并进行奖励或惩罚。
• 一种新颖的归一化技术在放宽均值/方差约束的同时对特征值进行界定，从而提高差分隐私扰动训练的准确性。

实验结果

研究问题

• RQ1 如何将区块链和差分隐私联邦学习整合，以安全地聚合来自分布式物联网参与者的模型？
• RQ2 与批量归一化相比，所提归一化技术在差分隐私下是否提升测试精度？
• RQ3 基于声誉的激励机制能否缓解中毒攻击并促进众包联邦学习中的参与者参与？
• RQ4 在以物联网为中心的联邦学习环境中，哪些存储和共识策略能够有效处理大型模型更新？

主要发现

• 将差分隐私应用于特征以保护参与者数据，同时实现有效的全局模型训练。
• 实验表明，所提归一化技术在差分隐私下的测试准确性高于批量归一化。
• 通过 IPFS 存储和 Algorand 共识实现的区块链审计防止篡改并实现模型更新的可追溯性。
• 结合声誉和 Multi-KRUM 的激励机制有助于识别可靠更新并遏制恶意贡献。