Smart and Secure CAV Networks Empowered by AI-Enabled Blockchain: The\n Next Frontier for Intelligent Safe Driving Assessment

Abstract

Securing safe driving for connected and autonomous vehicles (CAVs) continues\nto be a widespread concern, despite various sophisticated functions delivered\nby artificial intelligence for in-vehicle devices. Diverse malicious network\nattacks are ubiquitous, along with the worldwide implementation of the Internet\nof Vehicles, which exposes a range of reliability and privacy threats for\nmanaging data in CAV networks. Combined with the fact that the capability of\nexisting CAVs in handling intensive computation tasks is limited, this implies\na need for designing an efficient assessment system to guarantee autonomous\ndriving safety without compromising data security. In this article we propose a\nnovel framework, namely Blockchain-enabled intElligent Safe-driving assessmenT\n(BEST), which offers a smart and reliable approach for conducting safe driving\nsupervision while protecting vehicular information. Specifically, a promising\nsolution that exploits a long short-term memory model is introduced to assess\nthe safety level of the moving CAVs. Then we investigate how a distributed\nblockchain obtains adequate trustworthiness and robustness for CAV data by\nadopting a byzantine fault tolerance-based delegated proof-of-stake consensus\nmechanism. Simulation results demonstrate that our presented BEST gains better\ndata credibility with a higher prediction accuracy for vehicular safety\nassessment when compared with existing schemes. Finally, we discuss several\nopen challenges that need to be addressed in future CAV networks.\n