@Article{cmc.2021.015568, AUTHOR = {Mohana Priya Pitchai, Manikandan Ramachandran, Fadi Al-Turjman, Leonardo Mostarda}, TITLE = {Intelligent Framework for Secure Transportation Systems Using Software-Defined-Internet of Vehicles}, JOURNAL = {Computers, Materials \& Continua}, VOLUME = {68}, YEAR = {2021}, NUMBER = {3}, PAGES = {3947--3966}, URL = {http://www.techscience.com/cmc/v68n3/42463}, ISSN = {1546-2226}, ABSTRACT = {The Internet of Things plays a predominant role in automating all real-time applications. One such application is the Internet of Vehicles which monitors the roadside traffic for automating traffic rules. As vehicles are connected to the internet through wireless communication technologies, the Internet of Vehicles network infrastructure is susceptible to flooding attacks. Reconfiguring the network infrastructure is difficult as network customization is not possible. As Software Defined Network provide a flexible programming environment for network customization, detecting flooding attacks on the Internet of Vehicles is integrated on top of it. The basic methodology used is crypto-fuzzy rules, in which cryptographic standard is incorporated in the traditional fuzzy rules. In this research work, an intelligent framework for secure transportation is proposed with the basic ideas of security attacks on the Internet of Vehicles integrated with software-defined networking. The intelligent framework is proposed to apply for the smart city application. The proposed cognitive framework is integrated with traditional fuzzy, crypto-fuzzy and Restricted Boltzmann Machine algorithm to detect malicious traffic flows in Software-Defined-Internet of Vehicles. It is inferred from the result interpretations that an intelligent framework for secure transportation system achieves better attack detection accuracy with less delay and also prevents buffer overflow attacks. The proposed intelligent framework for secure transportation system is not compared with existing methods; instead, it is tested with crypto and machine learning algorithms.}, DOI = {10.32604/cmc.2021.015568} }