International Congress of Electrical and Computer Engineering, cilt.436, ss.203-215, 2022 (Scopus)
SCADA networks, which are widely used by governments around the world to run computers and applications that perform a wide range of important functions and provide critical services to their infrastructure, are becoming increasingly popular among organizations. Because of their critical role in the infrastructure, as well as the fact that they are a potential target for cyberattacks, they must be secured and protected in some way at all times. In this study, we propose a topic-based pub/sub messaging system based on Apache Spark and Apache Kafka for real-time monitoring and detection of cyber-physical attacks in SCADA systems, which can be used in conjunction with other currently available systems. There are a variety of traditional machine learning approaches used in conjunction with a deep learning encoded decoder algorithm to create the mechanism for attack detection. The performance results demonstrate that our system outperforms the current state of the art described in the literature in this field.