Machine Learning for Intrusion Detection in Vehicular Ad-hoc Networks (VANETs): A Survey
Nesmah A. AL-Khulaidi, Ammar T. Zahary, Asma A. Al-Shargabi, Muneer A. S. Hazaa
Abstract
Intrusion Detection Systems (IDSs) have become a key security problem due to the increasing number of connected automobiles and the sensitive nature of the data transferred in Vehicular Ad-hoc Networks (VANETs). By keeping an eye on network traffic, spotting questionable activity, and putting countermeasures in place to lessen risks, IDSs protect the integrity and security of VANETs. For VANETs, this study explores the state-of-the-art in machine learning-based IDSs, with a particular emphasis on work released in 2020–2022. We provide a thorough analysis of developments in widely used machine learning methods used for VANET intrusion detection throughout this time. This investigation explores certain machine learning methods that have been recently applied to VANET IDSs. The survey ends with a summary of the current issues and an exploration of potential directions for further investigation.