Intrusion detection systems for the internet of vehicles: a systematic survey of techniques and challenges across CAN bus and vehicular networks
Journal of Supercomputing, cilt.82, sa.12, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 82 Sayı: 12
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s11227-026-08772-3
- Dergi Adı: Journal of Supercomputing
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Applied Science & Technology Source, Compendex, INSPEC, zbMATH, Academic Search Ultimate (EBSCO), Biomedical Reference Collection: Corporate Edition (EBSCO), Engineering Source (EBSCO), Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: Cyber security, In vehicle network, Internet of vehicles, Intrusion detection systems
- Marmara Üniversitesi Adresli: Evet
Özet
The Internet of Vehicles (IoV) represents a rapidly expanding network of connected vehicles where real-time data exchange improves transportation efficiency and safety. However, the integration of IoV into everyday life also exposes it to significant cybersecurity threats, including distributed denial of service (DDoS) attacks, spoofing, and man-in-the-middle (MITM) attacks. Securing these environments is fundamentally a high-performance computing challenge: intrusion detection systems must process thousands of CAN bus frames per second, coordinate across distributed vehicular nodes, and execute inference within sub-millisecond latency budgets − requirements that necessitate GPU-accelerated pipelines, FPGA-based embedded deployment, and distributed edge computing architectures. Deep learning has emerged as a powerful tool to detect these complex cyberattacks due to its ability to analyse large amounts of data and identify anomalies in complex, dynamic systems such as IoV. This paper presents a comprehensive and systematic review of deep learning techniques applied to cyber intrusion detection within IoV systems, conducted in accordance with the PRISMA framework across 83 selected studies published between 2020 and 2025. In addition, the paper discusses the unique challenges that IoV presents, such as real-time processing requirements, limited computational resources, and the need for scalable, robust security frameworks. Despite significant advancements, the paper identifies several gaps in the literature, such as the scarcity of IoV-specific datasets, challenges in real-time detection, and the integration of privacy-preserving techniques. Future research directions are suggested to address these gaps by focusing on the development of more efficient, privacy-aware and hybrid deep learning models capable of detecting a wide range of cyber threats in IoV environments.