A lightweight intrusion detection system for internet of vehicles based on transfer learning and MobileNetV2 with hyper-parameter optimization

With the rapid development of Internet of Vehicles (IoV) technology, Intelligent Connected Vehicles (ICVs) have richer vehicle information functions and applications. In recent years, as ICVs have become more complex and intelligent, vehicle information security is facing great threats and challenges. Therefore, it is of great significance to develop efficient intrusion detection methods to protect the information security of IoV. In this paper, after analyzing the vulnerability of intra-vehicle networks (IVNs) and external vehicle networks (EVNs), we propose a lightweight intrusion detection method, which uses MobileNetv2 as the backbone, combines transfer learning (TL) techniques and the hyper-parameter optimization (HPO) method. The proposed method can detect various types of attacks, and the Accuracy, Precision, and Recall on the Car-Hacking dataset representing IVNs data are all 100 %. The Accuracy, Precision, and Recall on the CICIDS2017 dataset representing EVNs data are all 99.93 %. The average processing time of each packet tested is about 0.75 ms, and the model space is 23 M. Experimental results demonstrate that the proposed intrusion detection method is effective and lightweight.