Paper Key : IRJ************624
Author: Anuradha
Date Published: 07 Jul 2024
Abstract
The rise of autonomous vehicles (AVs) necessitates robust security measures to countercyberattacks. This abstract explores the vulnerability of AVs to attacks targeting sensors,communication networks, and software. It emphasizes the potential of machine learning (ML)for intrusion detection in AVs. By analyzing sensor data, network traffic, and system logs, MLalgorithms can identify anomalies indicative of attacks.This abstract underscores the significanceof IDS in protecting critical data and maintaining a secure network environment.This paperexplores the application of Random Forest classifiers in detecting these attacks, leveraging theirrobustness and ability to handle high-dimensional data. We present a detailed analysis ofthe methodology, dataset preparation, feature selection, and model evaluation. Our resultsdemonstrate that the Random Forest classifier effectively identifies and classifies different typesof attacks, providing a reliable tool for enhancing the security of autonomous vehicles. Thisexplores the application of Intrusion Detection Systems (IDS) for safeguarding AVs againstthese threats.The abstract highlights prominent ML techniques like supervised learning (SVMs,Random Forests), unsupervised learning (Isolation Forests, LOF), and deep learning (LSTMs)for anomaly and attack detection. This paper explores the application of machine learning (ML)algorithms for intrusion detection in AVs and concludes by highlighting research challenges andfuture directions in this critical field.
DOI Requested