Using Discriminant Analysis to Detect Intrusions in External Communication of Self-Driving Vehicles

Security systems are considered a necessity for the deployment of smart vehicles in our society. Security in vehicular ad hoc networks is crucial to the reliable exchange of information and control data. In this paper, an intelligent intrusion detection system (IDS) is proposed to protect the external communication of self-driving and semi self-driving vehicles. This technology has the ability to detect Denial of Service (DoS) and black hole attacks on VANETs. The advantage of the proposed IDS over incumbent security systems is that it detects the attack before it causes significant damage. The intrusion prediction technique is based on a Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA) to predict the attack based on an observed vehicle behaviour. Simulations utilised Network Simulator version 2 to demonstrate that the IDS exhibits a low rate of false alarms and high accuracy in detection. c © 2015 Published by Elsevier Ltd.