DECISION SUPPORT FOR RESPONDING TO ATTACKS IN CYBERPHYSICAL INDUSTRIAL INTERNET-OF-THINGS SYSTEMS

Abstract

Industrial Internet-of-Things (IIoT) systems have emerged as a foundational technology underpinning a wide range of modern applications, including environmental monitoring, healthcare systems, industrial automation, and smart infrastructures. Their inherent advantages incorporate scalability, low energy consumption, intelligence and programmability, rapid data acquisition, reliability, low cost, and the absence of maintenance requirements. At the same time, they attract the attention of attackers, making the task of ensuring the security of such networks crucial. This study introduces a comprehensive decision support methodology for responding to cyberattacks in IIoT systems, including systems using edge computing principles, based on analytical modeling for the analysis of networks, attacks, and countermeasures. The methodology also employs machine learning, rules, and multi-criteria optimization for attack detection and countermeasure selection. It consists of three stages: data collection on events occurring in the system, detection of attacks and anomalies, and selection of countermeasures for the identified attacks. Within the framework of the methodology, models of networks, attacks, and countermeasures, specific for IIoT systems, are presented. The main components and topology of IIoT systems are considered within the network model. The main types of attacks and possible countermeasures for IIoT systems are identified to specify the models of attacks and countermeasures. The algorithm for countermeasure selection within the proposed methodology based on rules and multi-criteria optimization and using the specified models is described. The application of the methodology is demonstrated through an example. The advantages and limitations of the proposed methodology are analyzed, and directions for future research are outlined.

More by Yerik Mardenov

• Propagation-Aware Agentic Defense Framework for Resilient Connected Autonomous Vehicle Cyber-Physical SystemsIEEE Vehicular Technology Conference · 2026
• Analysis of vulnerability databases for wireless networks in the Internet of Things for threat modellingDMPedia Lecture Notes in Computer Science & Engineering · 2026
• Trustworthy Anomaly Detection in Industrial IoT-Enabled Cyber-Physical Systems Using Explainable Ensemble LearningProceedings of the AAAI Symposium Series · 2026
• AI-AUGMENTED PENTESTING: SECURING IIOT AND SMART CITIESBulletin of the National Engineering Academy of the Republic of Kazakhstan · 2026