Intrusion Detection in Higher Educational Institution using Industrial Internet of Things through Software Defined Network

The focus of the presented work is to identify and prevent intrusion using Industrial Internet of Things. The motivation behind this work is a huge University data especially the dissertation and Thesis which are of immeasurable intellectual property significance if commercialized properly. The idea here is to protect this IP potential documents from getting espionage besides other important documents. "Industrial Internet of Things (IIOT)" is application of Internet of Things (IoT) to industrial management, where many machines and equipment are connected and synchronized to increase overall productivity through third-party platforms and software. Benefits of industrial IoT acquisition include automation, optimization, removal of manual operations, and increased overall efficiency; nevertheless, security still has to be considered. Improving IIoT security is hampered by the size of security features and the lack of trustworthy security solutions. Alarming attacks using IIoT network device vulnerabilities have been observed within the past several years. Furthermore, the attackers can delve further into the network by taking advantage of the connections inside the vulnerabilities. These kinds of network security risks cost industries and companies’ money, harm their reputations, and result in the theft of critical data. This study suggests an SDN-based intrusion detection system for industrial IoT environments that uses machine learning performances. The potential cost savings of implementing this system are significant, as it can identify attacks on IIoT networks and devices with 99.7% accuracy, thereby reducing the financial impact of these security risks. SDN is a methodology that allows software applications to govern a network intelligently and centrally. The SDN controller in our system analyzes traffic flow data and then applies a machine-learning algorithm to watch industrial IoT devices and network behavior before developing SDN switch flow rules.