An integrated IDS for the Internet of Vehicles using a Large Language Model framework

Abstract

The Internet of Vehicles (IoV) has expanded through the integration of VANET (Vehicular Ad hoc Network) and IoT (Internet of Things) technologies within the Intelligent Transportation System domain, facilitated by the advancement of Beyond 5G communication technology. Recently, smart vehicles, such as connected vehicles, have become increasingly prevalent due to technological advancements. These vehicles engage in communication with other IoV components, rendering them susceptible to various attacks. Ensuring the security of connected vehicles is crucial to mitigate vulnerabilities within the IoV environment, as cyber–physical threats could pose life-threatening consequences. Therefore, anomaly and attack detection mechanisms are imperative to safeguard the IoV environment. This paper proposes a Generative AI-based Intelligent Integrated Intrusion Detection System tailored for IoV, considering multiple communication dimensions. Typically, attackers may target both the in-vehicle network such as CAN (Controller Area Network) BUS, and various external networks such as DSRC (Dedicated Short-Range Communication), CV2X (Cellular Vehicle-to-Everything) of smart connected vehicles. Thus, an Intrusion Detection System (IDS) focusing on multi-communication dimension attacks on smart vehicles is developed to enhance safety, thereby preventing collisions and chaos. The TON_IoT dataset and CICIoV2024 dataset are used in this study to assess the proposed approach for detecting intra and inter-vehicular network attacks. The proposed work achieves promising results, having a high accuracy of 98% with a 96% detection rate and a high F1 score of 0.97.