Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

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 a 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 (DP) on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under DP protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

I. Introduction

Internet-of-Things (IoT)-enabled smart home systems have gained great popularity in the last few years since they have an aim to increase the quality of life. A report by Statista [1] estimates that by 2022, the smart home market size around the world will be 53.3 billion. This smart home concept is mainly enabled by IoT devices, smart phone, modern wireless communications, cloud & edge computing, big data analytics, and artificial intelligence (AI). In particular, these advanced technologies enable manufacturers to maintain a seamless connection among their smart home appliances. With the proliferation of smart home devices, tremendous data are generated. Federated learning (FL) enables analysts to analyze and utilize the locally generated data in a decentralized way without requiring uploading data to a centralized server; that is, the utility of data are well maintained despite data are preserved locally. To help home appliance manufacturers smartly and conveniently use data generated in customers’ appliances, we design an FL-based system. Our system considers home appliances of the same brand in a family as a unit, and a mobile phone is used to collect data from home appliances periodically and train the machine learning model locally [2]. Since mobile phones have limited computational power and battery life, we offload part of the training task to the edge computing server. Then, the blockchain smart contract is leveraged to generate a global model by averaging the sum of locally trained models submitted by users. In this federated way, source data are supposed to maintain security and privacy.