[论文解读] Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System.

Yang Zhao, Jun Zhao+3 more|arXiv (Cornell University)|Jun 26, 2019

Privacy-Preserving Technologies in Data参考文献 9被引用 81

一句话总结

本文提出了一种安全、去中心化且保护隐私的联邦学习系统，专为物联网设备制造商设计，该系统利用移动边缘计算、区块链和基于声誉的众包机制。它使用户能够使用本地收集的物联网数据协作训练个性化模型，并通过差分隐私保护用户隐私，同时区块链确保无需信任的模型聚合，激励机制则通过代币奖励鼓励用户参与。

ABSTRACT

Internet-of-Things (IoT) companies strive to get feedback from users to improve their products and services. However, traditional surveys cannot reflect the actual conditions of customers' due to the limited questions. Besides, survey results are affected by various subjective factors. In contrast, the recorded usages of IoT devices reflect customers' behaviours more comprehensively and accurately. We design an intelligent system to help IoT device manufacturers to take advantage of customers' data and build a machine learning model to predict customers' requirements and possible consumption behaviours with federated learning (FL) technology. The FL consists of two stages: in the first stage, customers train the initial model using the phone and the edge computing server collaboratively. The mobile edge computing server's high computation power can assist customers' training locally. Customers first collect data from various IoT devices using phones, and then download and train the initial model with their data. During the training, customers first extract features using their mobiles, and then add the Laplacian noise to the extracted features based on differential privacy, a formal and popular notion to quantify privacy. After achieving the local model, customers sign on their models respectively and send them to the blockchain. We use the blockchain to replace the centralized aggregator which belongs to the third party in FL. In the second stage, miners calculate the averaged model using the collected models sent from customers. By the end of the crowdsourcing job, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. Besides, to attract more customers to participate in the crowdsourcing FL, we design an incentive mechanism, which awards participants with coins that can be used to purchase other services provided by the company.

研究动机与目标

• 通过利用实际的物联网设备使用数据，解决传统调查在捕捉真实用户行为方面的局限性。
• 使物联网制造商能够在不损害用户隐私的前提下，构建用户行为的精准预测模型。
• 通过用基于区块链的去中心化模型聚合过程替代传统的集中式聚合器，消除联邦学习中对集中式聚合器的依赖。
• 通过基于代币的奖励机制，激励用户参与众包联邦学习。
• 通过与区块链集成的声誉系统，确保模型完整性和参与者问责性。

提出的方法

• 用户通过智能手机收集物联网使用数据，并在移动设备上执行本地模型训练，同时进行特征提取。
• 在本地模型训练前，通过向提取的特征添加拉普拉斯噪声来实施差分隐私。
• 每位用户使用数字签名对其本地模型进行签名，以确保真实性和完整性。
• 本地模型被提交至区块链，取代联邦学习中传统的集中式聚合器。
• 区块链上的矿工通过平均参与者提交的签名本地模型来计算全局模型。
• 临时领导者矿工将最终聚合的模型上传至区块链，以确保最终性和透明性。

实验结果

研究问题

• RQ1 如何设计一种去中心化的联邦学习框架，以在保护用户隐私的同时，基于物联网设备数据实现准确的模型训练？
• RQ2 区块链在替代集中式聚合器和确保联邦学习中无信任模型聚合方面发挥什么作用？
• RQ3 如何在本地训练阶段有效集成差分隐私，以保护用户数据？
• RQ4 何种激励机制能够有效鼓励广泛用户参与众包联邦学习？
• RQ5 在去中心化、无信任的环境中，如何维护物联网联邦学习中的声誉和问责性？

主要发现

• 移动边缘计算的集成显著降低了终端用户设备的计算负担，实现了高效的本地模型训练。
• 向特征添加拉普拉斯噪声确保了差分隐私，定量保护了用户数据在本地训练期间的安全。
• 基于区块链的模型聚合消除了对可信中心权威机构的依赖，增强了系统的去中心化和可信度。
• 基于代币的激励机制成功鼓励了用户参与，奖励根据贡献度和声誉进行分配。
• 通过多层信任与安全架构，系统在模型准确性、隐私保护和去中心化之间实现了良好平衡。