Offloading-verified framework for adversary detection and mitigation in IoT

Abstract

Cyber-physical systems (CPSs) designed for the Internet of Things (IoT) enhanced security and resource infrastructures to support various applications and services, undetected adversaries in the temporarily connected IoT network impose different user and data privacy threats, this research introduces an Offloading-verified Adversary Detection and Mitigation Scheme (OADMS), this proposed scheme coexists with the IoT communication and CPS security infrastructure for adversary detection, conventional behavior-based adversary detection with partial order adversarial network training validates the infrastructure security support against cyber-attacks. The behavior is analyzed for independent and offloaded service exchanges, reducing communication failures and is recurrently analyzed in the detection process until the service termination, communication metrics of the infrastructure units are used to verify adversary and user channel behavior. The learning process recommendations are exploited to validate the channel's reliability through IoT-sharing platforms, and the performance of the proposed system is assessed using communication latency, failure rate, response ratio, and detection factor. The model achieved an excellent detection accuracy rate of 96.8 %.