Misbehavior Detection in C-ITS Using Deep Learning Approach

Abstract

Cooperative Intelligent Transportation Systems (C-ITS) is one of the most prominent solutions to facilitate many new exciting applications concerning road safety, mobility, environment, and driving comfort. This technology is now on the verge of actual deployments. However, security threats, privacy, and trust management remain the most significant concerns. C-ITS relies highly on node cooperation and trust as vehicles take the decision based on the information received from the roadside network infrastructure. This information should be accurate and reliable to ensure proper functioning of the system. However, the presence of a misbehaving or compromised node in the system can lead to catastrophic results for both safety and traffic efficiency. It is therefore essential to detect misbehavior and defend the C-ITS against it. Although various studies have proposed misbehavior detection at the vehicular plane, the study that explores the machine learning capabilities to detect misbehavior at infrastructure plane is not present. Thus, in this paper, we propose a solution to detect misbehavior at the infrastructure plane of C-ITS that employs the predictive capabilities of Deep Learning. We compare the performance of Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) models of Deep Neural Network.