M.H. Ali and M. Basnet
University of Memphis,
Keywords: cybersecurity, electric vehicles, electric vehicle charging station, 5G, intrusion detection system
Summary:The surging usage of electric vehicles (EVs) demand the robust deployment of trustworthy electric vehicle charging station (EVCS). EVCS has to communicate with the incoming EVs for scheduling, charging EVs for authentication and authorization, and grids for efficiently utilizing the available energy through wired/wireless media. Therefore, EVCS is always vulnerable to cyber-attacks. The automation of EVCS operation and management requires remote centralized control like a supervisory control and data acquisition (SCADA) system that can communicate with numerous field devices with the least possible delay. 5G being the proven cellular technology with less than 1 ms latency and capable of millions of machine type communication, can be the candidate technology for EVCS communication. However, 5G suffers from inherent protocols, hardware, and software vulnerabilities that can seriously threaten the communicating entities' cyber-physical security. To overcome these limitations, this work analyzes the impact of various cyber-attacks such as the False Data Injection (FDI), Distributed Denial of Services (DDoS) attacks, etc., on the operation of EVCS. We propose the novel stacked Long Short-Term Memory (LSTM) based intrusion detection system (IDS) to detect the stealthy cyber-attacks that bypass the cyber layer and go unnoticed in the monitoring system with nearly 100% detection accuracy.