Rendering Secure and Trustworthy Edge Intelligence in 5G-Enabled IIoT Using Proof of Learning Consensus Protocol

【Author】 Qiu, Chao; Aujla, Gagangeet Singh; Jiang, Jing; Wen, Wu; Zhang, Peiying

【Source】IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS

【影响因子】11.648

【Abstract】Industrial Internet of Things (IIoT) and fifth generation (5G) network have fueled the development of Industry 4.0 by providing an unparalleled connectivity and intelligence to ensure timely (or real time) and optimal decision-making. Under this umbrella, the edge intelligence is ready to propel another ripple in the industrial growth by ensuring the next generation of connectivity and performance. With the recent proliferation of blockchain, edge intelligence enters a new era, where each edge trains the local learning model, then interconnecting the whole learning models in a distributed blockchain manner, known as blockchain-assisted federated learning. However, it is quiet challenging task to provide secure edge intelligence in 5G-enabled IIoT environment alongside ensuring latency and throughput. In this article, we propose a proof-of-learning consensus protocol that considers the reputation opinion for edge blockchain to ensure secure and trustworthy edge intelligence in IIoT. This protocol fetches each edge's reputation opinion by executing a smart contract, and partly adopts the winner's learning model according to its reputation opinion. By quantitative performance analysis and simulation experiments, the proposed scheme demonstrates the superior performance in contrast to the traditional counterparts.

【Keywords】Industrial Internet of Things; Training; Security; Consensus protocol; Protocols; Artificial intelligence; Task analysis; Blockchain; edge intelligence; industrial Internet of Things (IIoT); proof of learning (PoL); reputation opinion

【发表时间】2023 JAN

【收录时间】2022-11-30

【文献类型】实验仿真

【主题类别】

区块链技术-协同技术-联邦学习