IoT-Enabled Threat Detection for Large-Scale Distributed Networks in Smart Policing
The purpose chapter objectives to design a scalable and intelligent threat detection system to smart policing networks that leverages the IoT technology at scale. It will deal with the problems of timely processing of data of various types of devices and security issues related to such devices. It is suggested to use a multi-layer architecture based on multi-modal (different forms of media) deep learning, near the source (edge) processing of data as well as federated (distributed) learning to provide/network intelligence to the threat detection system. The system is a combination of CNN-BLSTM-based feature learning and adaptive decision mechanisms to allow real-time detection and response. The hybrid dataset of benchmark intrusion data, real IoT traffic, and simulated attack scenarios are used to validate this experiment. The proposed framework has a high detection accuracy (96.7%) and low latency (~280 ms), which is better than the traditional, machine learning, and state-of-the-art deep learning models.