A Secured Cognitive Science Based Hybrid Framework to Detect DDOS Attacks in Intelligent Transport Systems ITS

Abstract

Intelligent Transportation Systems (ITS) aim to improve traffic flow, newlinesafety, and accident statistics by leveraging the synergy of the Internet of Vehicles newline(IoV) and the Internet of Things (IoT). These systems face challenges and newlinevulnerabilities related to authentication, credentialing, availability, privacy, data newlinerouting, and the legitimacy of data. They operate within large-scale infrastructure newlinenetworks featuring dynamic topology structures, uneven node distribution, and free newlinenode mobility across extensive areas. This study focuses on achieving three specific newlineobjectives: detecting Distributed Denial of Service (DDoS) flooding attacks, analyzing newlineDDoS attacks, and enhancing situational awareness using principles of cognitive newlinescience. The primary focus is on detecting and mitigating DDoS flooding attacks that newlinedisrupt the operational capability of Road Side Units (RSUs) within the Intelligent newlineTransportation Systems (ITS) framework while bypassing traditional data filtering newlineapproaches. The proposed approach employs reinforcement learning to detect DDoS newlineflooding attacks, addressing the security challenges in ITS and advancing beyond newlineexisting detection methods for modern vehicular systems. It incorporates a Q-learning newlinealgorithm to mitigate flooding attacks, enhancing the overall security of ITS newline

Description

Keywords

Citation

item.page.endorsement

item.page.review

item.page.supplemented

item.page.referenced