Artificial Intelligence in Vehicular Networks: A Comprehensive Review of Security Challenges and Defenses
Abstract
The integration of artificial intelligence (AI) into vehicular networks has fundamentally transformed intelligent transportation systems, enabling autonomous driving, cooperative perception, and real-time traffic management. However, this convergence has simultaneously expanded the security attack surface, creating novel vulnerabilities that traditional cryptographic defenses alone cannot address. This comprehensive review examines the intersection of AI, vehicular networks, and security, providing a systematic analysis of emerging threats and defense mechanisms. We first establish the architectural foundations of modern vehicular networks, tracing the evolution from Vehicular Ad Hoc Networks (VANETs) to the Internet of Vehicles (IoV) and AI-native V2X systems. We then present a multi-layered threat taxonomy encompassing traditional protocol-level attacks and AI-specific vulnerabilities, including adversarial examples, data poisoning, model inversion, and Byzantine attacks in federated learning environments. Our analysis of defense mechanisms covers machine learning-based intrusion detection systems, blockchain-assisted trust management, federated learning with privacy preservation, and adversarial robustness techniques. We identify critical research gaps, particularly the disconnection between theoretical attack demonstrations and real-world validation, the tension between privacy preservation and detection efficacy, and the unresolved challenge of securing distributed…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.