An ML-Based Authentication for Privacy Preservation in a Distributed Edge-Enabled Internet of Vehicles

In the Internet of Vehicles (IoV), privacy preservation is a major challenge due to the mobility of vehicles and their resource-constrained nature. The limited resources of on-board units (OBUs) and embedded sensors lure the adversaries to launch various types of attacks. Thus, lightweight but reliable authentication schemes need to be designed to combat these attacks. Another major challenge is the scarcity of available bandwidth and excessive delay experienced by vehicles while they communicate with the servers located at the cloud. These servers execute various machine learning (ML) and deep learning (DL) algorithms to extract useful features from upstream traffic of IoV. To addresses these challenges, we propose an ML-based authentication scheme that trains and classifies the vehicles at the edge servers in a distributed manner, preserves the privacy of communicating entities and minimizes the bandwidth consumption and delay experienced by the vehicles. The ML-based approach extends the decision power of vehicles and edge servers to identify adversaries. Our scheme requires that each vehicle participates in an offline phase, where a trusted authority shares a list of MaskIDs and secret keys of legitimate vehicles and edge servers. A timestamp is embedded in the payload of each encrypted message to prune the proposed scheme against well-known adversarial attacks. The simulation results verify the exceptional performance of our scheme in terms of computational overhead, communication overhead, and storage overhead.