Machine Learning-Based Detection for Cyber Security Attacks on Connected and Autonomous Vehicles

Abstract

Connected and Autonomous Vehicle (CAV)-related initiatives have become some of the fastest expanding in recent years, and have started to affect the daily lives of people. More and more companies and research organizations have announced their initiatives, and some have started CAV road trials. Governments around the world have also introduced policies to support and accelerate the deployments of CAVs. Along these, issues such as CAV cyber security have become predominant, forming an essential part of the complications of CAV deployment. There is, however, no universally agreed upon or recognized framework for CAV cyber security. In this paper, following the UK CAV cyber security principles, we propose a UML (Unified Modeling Language)-based CAV cyber security framework, and based on which we classify the potential vulnerabilities of CAV systems. With this framework, a new CAV communication cyber-attack data set (named CAV-KDD) is generated based on the widely tested benchmark data set KDD99. This data set focuses on the communication-based CAV cyber-attacks. Two classification models are developed, using two machine learning algorithms, namely Decision Tree and Naive Bayes, based on the CAV-KDD training data set. The accuracy, precision and runtime of these two models when identifying each type of communication-based attacks are compared and analysed. It is found that the Decision Tree model requires a shorter runtime, and is more appropriate for CAV communication attack detection.

Sensor Data Based Anomaly Detection in Autonomous Vehicles using Modified Convolutional Neural Network

“…He et al [19] introduced a CAV cyber protection architecture centered on UML (Unified Modeling Language) to describe CAV networks' possible attacks. Depending on the training data, two classification methods were presented.…”

CNN‐OHGS: CNN‐oppositional‐based Henry gas solubility optimization model for autonomous vehicle control system

“…The severity assessment model regarding the autonomous and connected vehicles for the potential cyber attack was proposed by He, Meng, Qu, and Xi (2020). Here numerous sets of potential attacks were gathered and examined from various aspects that include risks, target assets, and consequences.…”

Untitled

“…Thus, a CAV cyber security framework categorizing communication-based attacks is proposed in this paper. To simulate the network attack scenarios, [28] uses the KDD99 data set which includes Probing attacks, Denial of Service attacks, User-to-Root attacks, and Remote-to-Local attacks. The KDD99 is a data set that is commonly used as a benchmark for attack detection or online intrusion for computer and network security.…”

“…In CAV networks connectivity and safety, an intrusion detection system is an important element as it assists in discriminating normal and anomalous behavior with relatively high accuracy. Most such systems are based on machine learning schemes and other schemes [26,28,31,32,34], such as the proportional overlapping scoring method [9].…”