Classifying DDoS Attack in Industrial Internet of Services Using Machine Learning

• Main Authors: Qaiser, Ghazia, Chandrasekaran, Siva, Chai, Rifai, Zheng, Jinchuan
• Format: Conference Proceeding
• Language: English
• Subjects: classification; DDos; Denial-of-service attack; industrial internet of services; Industries; Machine learning; Machine learning algorithms; Production; Real-time systems; Time measurement
• ISSN: 2154-4360
• DOI: 10.1109/ICCAE56788.2023.10111178

There were various research articles proposed different IIoT and Industrial Internet of Services (IIoS) techniques for Industry 4.0 innovative practices. At the same time, the concept of IIoS is considered a critical enabler for smart industries. Therefore, IIoT has evolved over time into an IIoS, which introduces servitization processes to measure product or service quality. The idea behind IIoS is to strategically use the Internet as a platform to assemble new value for the services sector in different industries. The IIoS is a vital aspect to consider for improving the final production line. However, at the same time, the internet's inherent vulnerability puts it at risk of cyber security attacks, particularly DDoS attacks.This research is focused on investigating DDoS vulnerabilities that can negatively impact IIoS. The study evaluates six machine learning algorithms in terms of their ability to detect DDoS attacks. The mentioned ML algorithms are renowned for data traffic classification within the existing literature. Moreover, this research can assist users in diagnosing potential DDoS threats and optimizing production lines.