An Intelligent Data-Driven Model to Secure Intravehicle Communications Based on Machine Learning

Abstract

The high relying of electric vehicles on either invehicle or between-vehicle communications can cause big issues in the system. This paper is going to mainly address the cyber attack in electric vehicles and propose a secured and reliable intelligent framework to avoid hackers from penetration into the vehicles. The proposed model is constructed based on an improved support vector machine model for anomaly detection based on the controller area network (CAN) bus protocol. In order to improve the capabilities of the model for fast malicious attack detection and avoidance, a new optimization algorithm based on social spider (SSO) algorithm is developed which will reinforce the training process at offline. Also, a two-stage modification method is proposed to increase the search ability of the algorithm and avoid premature convergence. Last but not least, the simulation results on the real data sets reveal the high performance, reliability and security of the proposed model against denial-of-service (DoS) hacking in the electric vehicles.