Securing Wireless Communications of Connected Vehicles with Artificial Intelligence

Abstract

This work applies artificial intelligence (AI) to secure wireless communications of Connected Vehicles. Vehicular Ad-hoc Network (VANET) facilitates exchange of safety messages for collision avoidance, leading to self-driving cars. An AI system continuously learns to augment its ability in discerning and recognizing its surroundings. Such ability plays a vital role in evaluating the authenticity and integrity of safety messages for cars driven by computers. Falsification of meter readings, disablement of brake function, and other unauthorized controls by spoofed messages injected into VANET emerge as security threats. Countermeasures must be considered at design stage, as opposed to afterthought patches, effectively against cyber-attacks. However, current standards oversubscribe security measures by validating every message circulating among Connected Vehicles, making VANET subject to denial-of-service (DoS) Attacks. This interdisciplinary research shows promising results by searching the pivot point to balance between message authentication and DoS prevention, making security measures practical for the real world deployment of Connected Vehicles. Message authentication adopts Context-Adaptive Signature Verification strategy, applying AI filters to reduce both communication and computation overhead. The results lead to an effective design choice of securing wireless communications for Connected Vehicles.

Existing System

Secure and efficient beaconing for vehicular networks.

Proposed System

This interdisciplinary research shows promising results of applying the artificial intelligence filters to secure the wireless communication of connected vehicles. Particle filter significantly reduces communication overhead while keeping the same detection level of spoofed messages when compared to Kalman filter in VANET applications. We explained that why vehicular networks are important, why networks must be secured and why vehicular networks are promising. Stimulating different scenarios with Context adaptive beacon verification along with Kalman and particle filter on University of Massachusetts Dartmouth and State Road (Dartmouth) proved that it can detect and prevent spoofed attacks and help reducing the computational overhead. The practice makes the autonomous cars the target of attack because of the number of spoofed messages missed by context adaptive beacon verification is performed which leaves the undetected rate too high to be replaced by conventional verification method.

Architecture

On-Board Unit