<![CDATA[Introduction: The rapid growth of the Internet of Things (IoT) has increased the number of connected devices and network traffic complexity, thereby intensifying cybersecurity risks within digital infrastructures. Conventional centralized security systems often experience detection delays, network bottlenecks, and performance degradation when deployed in large-scale IoT environments. Objective: This study aims to design and evaluate a Hybrid GenAI Edge framework that integrates Generative Artificial Intelligence (GenAI) with edge-based intrusion detection mechanisms to enhance detection accuracy, response speed, and system scalability in IoT networks. Methods: A quantitative experimental approach was employed using a controlled large-scale IoT network simulation environment. The dataset consisted of normal traffic, various IoT attack types, and synthetic attack data generated by a generative model to enrich threat pattern diversity. System performance was evaluated using accuracy, precision, recall, F1-score, false positive rate, detection latency, resource utilization, and scalability testing based on increasing numbers of IoT devices. Results: The findings indicate that the Hybrid GenAI Edge framework achieved a detection accuracy of 96.7%, significantly reduced the false positive rate, and lowered detection latency compared to the centralized architecture. Moreover, the system maintained stable performance as the number of IoT devices increased, demonstrating its potential as an adaptive, efficient, and scalable cybersecurity solution for modern IoT infrastructures.]]>
Copyrights © 2023
