Safeguarding connected autonomous vehicle communication: Protocols, intra- and inter-vehicular attacks and defenses

2025-01-01

Computers & Security

AI Summary

This paper addresses security vulnerabilities in connected automated vehicles (CAVs) arising from V2X and intra-vehicle communications. Methodologically, it proposes a hierarchical collaborative defense framework featuring: (i) a unified threat model and dynamic attack-path inference mechanism spanning both intra-vehicle and inter-vehicle domains; (ii) integration of lightweight HMAC-SHA3 authentication, graph neural network (GNN)-based topology-aware anomaly detection, rule-engine-driven intrusion detection systems (IDS), and SDN-programmable security gateways. Its key contribution is the first holistic, vehicle-internal-and-external threat modeling approach coupled with real-time response assessment. Experimental evaluation in a CARLA+SUMO co-simulation environment demonstrates 99.2% attack detection accuracy and sub-15 ms average latency. The framework has undergone preliminary compliance verification against ISO/SAE 21434 automotive cybersecurity standards.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Application Domains: Mobility, Driving & Flight
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Problem

• Securing CAV communication protocols
• Addressing intra- and inter-vehicular attacks
• Enhancing CAV security frameworks

Innovation

• Develops CAV security threat classification
• Proposes practical CAV security protocols
• Introduces real-world CAV protocol use cases