A Redactable Blockchain Framework for Secure Federated Learning in Industrial Internet of Things

Industrial Internet of Things (IIoT) facilitate private data collecting via (a broad range of) sensors, and the analysis of such data can inform decision making at different levels. Federated learning (FL) can be used to analyze the collected data, in privacy-preserving manner by transmitting model updates instead of private data in IIoT networks. The FL framework is, however, vulnerable because model updates are easily tampered with by malicious agents. Motivated by this observation, we propose a novel chameleon hash scheme with a changeable trapdoor (CHCT) for secure FL in IIoT settings. Our scheme imposes various constraints on the use of trapdoor. We give a rigorous security analysis on our CHCT scheme. We also instantiate the CHCT scheme as a redactable medical blockchain (RMB). The experimental evaluations demonstrate the practical utility of CHCT in terms of accuracy and efficiency.

I. Introduction

The rapid development of the Internet of Things (IoT) technology makes it possible for smart devices to communicate with each other [1]–[3]. Industrial Internet of Things (IIoT) data is of great significance to the management and monitoring of industrial processes, which usually has obvious structural characteristics and has a huge data volume. It is important to store, manage, and analyze these data securely and efficiently since the data generated by IIoT have great value and can be used to extract knowledge. In a traditional IIoT structure [4], [5], a centralized database or cloud server is employed to collect, manage, and analyze all the data. For a long time, the common practice is that factories centrally store the industrial data from IIoT in a database, and the factories are responsible for managing and analyzing the industrial data. This centralized data processing method is conducive to management, but it has problems in data security and privacy protection. Li et al. [6] analyzed the drawbacks of this common practice in terms of security privacy protection, and focuses on the necessity of using blockchain to realize the distributed data storage and protection in IIoT networks.