Deep Transfer Learning Techniques in Intrusion Detection System-Internet of Vehicles: A State-of-the-Art Review

Abstract

The high performance of IoT technology in transportation networks has led to the increasing adoption of Internet of Vehicles (IoV) technology. The functional advantages of IoV include online communication services, accident prevention, cost reduction, and enhanced traffic regularity. Despite these benefits, IoV technology is susceptible to cyber-attacks, which can exploit vulnerabilities in the vehicle network, leading to perturbations, disturbances, non-recognition of traffic signs, accidents, and vehicle immobilization. This paper reviews the state-of-the-art achievements and developments in applying Deep Transfer Learning (DTL) models for Intrusion Detection Systems in the Internet of Vehicles (IDS-IoV) based on anomaly detection. IDS-IoV leverages anomaly detection through machine learning and DTL techniques to mitigate the risks posed by cyber-attacks. These systems can autonomously create specific models based on network data to differentiate between regular traffic and cyberattacks. Among these techniques, transfer learning models are particularly promising due to their efficacy with tagged data, reduced training time, lower memory usage, and decreased computational complexity. We evaluate DTL models against criteria including the ability to transfer knowledge, detection rate, accurate analysis of complex data, and stability. This review highlights the significant progress made in the field, showcasing how DTL models enhance the performance and reliability of IDS-IoV systems. By examining recent advancements, we provide insights into how DTL can effectively address cyber-attack challenges in IoV environments, ensuring safer and more efficient transportation networks.