Generative AI-based intrusion detection systems for intra-vehicle networks

Abstract

With the rise of connected and autonomous vehicles, securing Intra-Vehicle Networks against cyber threats has become a critical challenge. The Controller Area Network bus, a widely used communication protocol in modern vehicles, remains highly vulnerable to sophisticated intrusion attacks. Traditional Machine Learning and Deep Learning based Intrusion Detection Systems have demonstrated limitations in adaptability, real-time performance, and handling zero-day attacks. This survey explores the emerging role of Generative Artificial Intelligence in enhancing IVN security. It examines key GenAI—assessing their potential to address the shortcomings of conventional IDS techniques. A comprehensive review of recent literature is conducted, analyzing the effectiveness of generative approaches in intrusion detection compared to deterministic methods. Key aspects such as detection time, adaptability to unknown threats, and real-time processing constraints are evaluated. Additionally, this paper identifies existing research gaps, emphasizing the need for standardized datasets, federated learning strategies, and improved deployment techniques to ensure the practical viability of GenAI-based IDS in real-world vehicular environments. The insights presented aim to guide future research toward more robust and adaptive security solutions for IVNs.