CYBERATTACK DETECTION METHODS AND DISTRIBUTION USING IOT-ENABLED CYBER-PHYSICAL SYSTEMS

Abstract

Authentication procedures designed for conventional information and operational technology systems fail in cyber-physical system (CPS) contexts, making it difficult to secure IoT-enabled CPS. Therefore, a cyber-intensive detection mechanism and identification approach based on CPS with an emphasis on control systems was utilized in the research. Maintaining the safety of CPS IoT systems relies on the attack detection and identification technologies offered. This strategy solves the disparities in CPS IoT data without excluding underrepresented groups or compromising the integrity of the data. When an attack occurs, the proposed framework can passively analyse sensor data and trigger an alert at the top of the protocol stack. The scenario's attribution model uses this information to infer the attacker's skills. In addition, the suggested platform's timely and fruitful data can help security researchers and emergency response teams react to attacks and prevent losses. The detection and prevention processes employ deeper representations to learn how to turn data into quicker dimensions, while DTs are used to identify attack data. There is significant worry about the security of IoT devices, which may include these vital resources. In addition, critical infrastructure is a major source of IoT connections. Thus, their vulnerabilities profoundly affect the context in which IoT devices are employed. Users and service providers alike will be increasingly cognizant of the need for privacy and anonymity due to the IoT. This study suggests a novel IoT-based cyber-physical system that employs dual strategies for detecting and dispersing cyber-attacks.