DETECTION AND ATTRIBUTION OF CYBER-ATTACKS IN IOT-ENABLED CYBER-PHYSICAL SYSTEMS

Abstract

This research focuses on Cyber-Physical Systems (CPS) that are facilitated by the Internet of Things (IoT). Their detection and attribution of cyberattacks are a primary concern, as these systems are widely used in critical infrastructures such as smart grids, healthcare, and industrial automation. As the number of devices connected and the variety of devices used increases, these systems are susceptible to sophisticated cyberattacks. The paper proposes an integrated framework for real-time malicious activity detection that employs anomaly detection techniques and machine learning. This framework is achieved by examining system interactions, device behavior, and network traffic. It also emphasizes the importance of attack attribution, which involves the utilization of source tracing, behavioral analysis, and pattern recognition to determine the origin and purpose of attacks. In comparison to conventional methods, the proposed model improves the reliability, security, and resilience of IoT-enabled CPS environments by enhancing detection accuracy, decreasing false positives, and improving attribution precisions.