Machine Learning for Security in Vehicular Networks: A Comprehensive Survey

Abstract

Machine Learning (ML) has emerged as an attractive and viable technique to provide effective solutions for a wide range of application domains. An important application domain is vehicular networks wherein ML-based approaches are found to be very useful to address various problems. The use of wireless communication between vehicular nodes and/or infrastructure makes it vulnerable to different types of attacks. In this regard, ML and its variants are gaining popularity to detect attacks and deal with different kinds of security issues in vehicular communication. In this paper, we present a comprehensive survey of ML-based techniques for different security issues in vehicular networks. We first briefly introduce the basics of vehicular networks and different types of communications. Apart from the traditional vehicular networks, we also consider modern vehicular network architectures. We propose a taxonomy of security attacks in vehicular networks and discuss various security challenges and requirements. We classify the ML techniques developed in the literature according to their use in vehicular network applications. We explain the solution approaches and working principles of these ML techniques in addressing various security challenges and provide insightful discussion. The limitations and challenges in using ML-based methods in vehicular networks are discussed. Finally, we present observations and lessons learned before we conclude our work.

Adversarial Attacks Against Deep Reinforcement Learning Framework in Internet of Vehicles

“…Driven by the dynamic nature of vehicles, deep reinforcement learning (DRL) has been a breakthrough technique for interactive and continual decision-making in IoVs. The use of DRL and its variants are widely explored in the literature to provide solutions toward motion planning and control, resource sharing, service placement, scheduling, security and many other aspects of vehicular networks [2]- [4].…”

“…In DRL, the policy is a neural network, and its framework contains an agent that interacts with the environment as it operates and makes a decision by rewarding the desired behavior and punishing the undesired one. The continual interaction of the DRL agent with the end-user exposes it to the number of adversarial attacks [4], [7]. The assumption of having a secure environment to interact is not satisfactory in vehicular applications where misbehavior from an attacker can be lifethreatening in case of accidents in vehicles.…”

“…Data poisoning attacks like label flipping, backdoor attack, and model poisoning attack are very common adversarial attacks and explored in the literature for vehicular applications [4]. In the context of DRL, where each time user feedback is collected to calculate reward, the effectiveness of an attack can increase using Sybils.…”