CascadMLIDS: A Cascaded Machine Learning Framework for Intrusion Detection System in VANET

Abstract

Vehicular ad hoc networks (VANETs) incorporating vehicles as an active and fast topology are gaining popularity as wireless communication means in intelligent transportation systems (ITSs). The cybersecurity issue in VANETs has drawn attention due to the potential security threats these networks face. An effective cybersecurity measure is essential as security threats impact the overall system, from business disruptions to data corruption, theft, exposure, and unauthorized network access. Intrusion detection systems (IDSs) are popular cybersecurity measures that detect intrusive behavior in a network. Recently, the machine learning (ML)-based IDS has emerged as a new research direction in VANET security. ML-based IDS studies have focused on improving accuracy as a typical classification task without focusing on malicious data. This study proposes a novel IDS for VANETs that offers more attention to classifying attack cases correctly with minimal features required by applying principal component analysis. The proposed Cascaded ML framework recognizes the difference between the attack and normal cases in the first step and classifies the attack data in the second step. The framework emphasizes that an attack should not be classified into the normal class. Finally, the proposed framework is implemented with an artificial neural network, the most popular ML model, and evaluated with the Car Hacking dataset. In addition, the study also investigates the efficiency of typical classification tasks and compares them with results of the proposed framework. Experimental results on the Car Hacking dataset have revealed the proposed method to be an effective IDS and that it outperformed the existing state-of-the-art ML models.