MTH-IDS: A Multitiered Hybrid Intrusion Detection System for Internet of Vehicles
A multitiered hybrid IDS that incorporates a signature- based IDS and an anomaly-based IDS is proposed to detect both known and unknown attacks on vehicular networks, and experimental results illustrate the feasibility of implementing the proposed system in real-time vehicle systems.
Abstract
Modern vehicles, including connected vehicles and autonomous vehicles,\nnowadays involve many electronic control units connected through intra-vehicle\nnetworks to implement various functionalities and perform actions. Modern\nvehicles are also connected to external networks through vehicle-to-everything\ntechnologies, enabling their communications with other vehicles,\ninfrastructures, and smart devices. However, the improving functionality and\nconnectivity of modern vehicles also increase their vulnerabilities to\ncyber-attacks targeting both intra-vehicle and external networks due to the\nlarge attack surfaces. To secure vehicular networks, many researchers have\nfocused on developing intrusion detection systems (IDSs) that capitalize on\nmachine learning methods to detect malicious cyber-attacks. In this paper, the\nvulnerabilities of intra-vehicle and external networks are discussed, and a\nmulti-tiered hybrid IDS that incorporates a signature-based IDS and an\nanomaly-based IDS is proposed to detect both known and unknown attacks on\nvehicular networks. Experimental results illustrate that the proposed system\ncan detect various types of known attacks with 99.99% accuracy on the\nCAN-intrusion-dataset representing the intra-vehicle network data and 99.88%\naccuracy on the CICIDS2017 dataset illustrating the external vehicular network\ndata. For the zero-day attack detection, the proposed system achieves high\nF1-scores of 0.963 and 0.800 on the above two datasets, respectively. The\naverage processing time of each data packet on a vehicle-level machine is less\nthan 0.6 ms, which shows the feasibility of implementing the proposed system in\nreal-time vehicle systems. This emphasizes the effectiveness and efficiency of\nthe proposed IDS.\n