Lightweight Privacy and Security Computing for Blockchained Federated Learning in IoT

Abstract

The development of Internet of Things (IoT) makes human life more intelligent, and the interconnection of all things has become a reality. However, the surge in the number of devices and centralized management brings severe challenges to IoT, such as single point of failure, poor security, privacy leakage, and low reliability. Due to the decentralization, verifiability and privacy protection of blockchain federated learning, some blockchain federated learning schemes have been proposed to solve these problems, but bring new challenges, such as device privacy leakage and heavy security computing load. In this paper, we propose a new decentralized, secure and verifiable consortium blockchain federated learning privacy protection scheme, named LPBFL, which realizes lightweight computing while ensuring the privacy of the local model and dataset of the device. To achieve lightweight privacy protection, LPBFL adopts the Paillier encryption and the newly designed lightweight digital signature and batch verification algorithm. Additionally, considering that devices upload invalid or even toxic local models intentionally or unintentionally, we design a device reputation selection mechanism to make blockchain federated learning more efficient. Finally, the theoretical analysis proves the security of LPBFL and verifies the unforgeability of the proposed digital signature. Comprehensive comparisons and extensive experiments demonstrate that our LPBFL has significant advantages in multiple aspects.