An effective intrusion detection scheme for Distributed Network Protocol 3 (DNP3) applied in SCADA-enabled IoT applications

Abstract

The widespread adoption of computers and the Internet in recent decades has led to a growing reliance on digital technologies. Supervisory Control and Data Acquisition (SCADA)-enabled Internet of Things (IoT) applications are now used in various sectors such as nuclear power plants, oil and gas extraction, and refineries. However, ensuring the security of computer networks and such autonomous systems is essential to thwart potential threats from hackers and intruders. In this article, an intrusion detection scheme is proposed by deploying different machine learning algorithms (referred to as IDM-DNP3). These algorithms are rigorously trained and tested on an extensive dataset encompassing nine Distributed Network Protocol 3 (DNP3) testbed attacks. Utilizing a range of algorithms, a multi-class classification model was successfully developed for detecting attacks related to SCADA and DNP3. The comparative study conducted shows that IDM-DNP3 can detect potential threats with higher accuracy than other existing schemes.