Akademik Veri Yönetim Sistemi
2025 Innovations in Intelligent Systems and Applications Conference, ASYU 2025, Bursa, Türkiye, 10 - 12 Eylül 2025, (Tam Metin Bildiri)
The rise of Over-the-Air (OTA) technology in automotive systems brings significant convenience and cost savings but also introduces new cyber-physical risks. In the context of connected and autonomous vehicles (CAVs), ensuring robust anomaly detection mechanisms becomes critical to counter evolving threats targeting in-vehicle networks such as the Controller Area Network (CAN) bus. This paper presents a comprehensive evaluation of anomaly detection methods for OTA-integrated automotive systems. We review statistical, machine learning, and deep learning approaches, with a particular focus on their suitability for real-time deployment under automotive constraints. Our analysis draws on recent advances in literature, compares detection efficacy, computational overhead, and real-world adaptability, and provides insights into future research directions for the secure integration of OTA capabilities. The results highlight that hybrid, context-aware models leveraging both payload and sequence-level information achieve state-of-the-art detection with minimal resource consumption. Recommendations are made for integrating robust anomaly detection into OTA update frameworks, balancing accuracy, interpretability, and efficiency.