Data-Driven Intrusion Detection for Intelligent Internet of Vehicles: A Deep Convolutional Neural Network-Based Method

As an industrial application of Internet of Things (IoT), Internet of Vehicles (IoV) is one of the most crucial techniques for Intelligent Transportation System (ITS), which is a basic element of smart cities. The primary issue for the deployment of ITS based on IoV is the security for both users and infrastructures. The Intrusion Detection System (IDS) is important for IoV users to keep them away from various attacks via the malware and ensure the security of users and infrastructures. In this paper, we design a data-driven IDS by analyzing the link load behaviors of the Road Side Unit (RSU) in the IoV against various attacks leading to the irregular fluctuations of traffic flows. A deep learning architecture based on the Convolutional Neural Network (CNN) is designed to extract the features of link loads, and detect the intrusion aiming at RSUs. The proposed architecture is composed of a traditional CNN and a fundamental error term in view of the convergence of the backpropagation algorithm. Meanwhile, a theoretical analysis of the convergence is provided by the probabilistic representation for the proposed CNN-based deep architecture. We finally evaluate the accuracy of our method by way of implementing it over the testbed.

I. Introduction

With the rapid development of Internet of Things (IoT), it has been extended to vehicles for structuring the Intelligent Transportation System (ITS), i.e., the intelligent Internet of Vehicles (IoV). The intelligent IoV can provide credible and efficient communication services for vehicles to support kinds of applications, e.g., the Global Positioning System (GPS) and the advanced driving assistance system [1]. It is one of the most crucial techniques for employing the ITS in order to realize smart cities. Recently, various networking techniques, such as the 5G-enable communication network, have been already involved in IoVs to provide the higher bandwidth for users. Subsequently, an increasing number of users’ private information is transmitted over IoVs. Furthermore, the IoV is an open network for each user, though the user may be a possible attacker. Due to the openness of the IoV, it is usually attacked by various malware (e.g., the worm and the Trojan horse). Meanwhile, the Distributed Denial of Service (DDoS) attack has been a main menace for vehicles, in which the flooding DDoS attack known as a brute-force attack exhausts the cache and computing resources of vehicles. Thereby, to protect the privacy and security of users, the intrusion detection techniques have obtained more and more attention in IoVs [2]–[7].