Effective Deep Learning-Based Attack Detection Methods for the Internet of Medical Things

Abstract

Recently, the internet of things (IoT) has evolved into a breakthrough for creating intelligent settings. Any technology's reliance on the IoT model is seen as having major security and privacy issues. The various conceivable attacks carried out by intruders give rise to privacy and security considerations. Therefore, creating an intrusion detection system is crucial for identifying attacks and anomalies in the IoT system. In this work, a deep belief network (DBN) algorithm model for the intrusion detection system has been proposed. The CICIDS 2017 dataset is used for the performance analysis of the current IDS model in terms of assaults and anomaly detection. Accuracy, recall, precision, F1-score, detection rate, and other characteristics were all improved by the proposed method. IoT technology has revolutionized how healthcare is provided to patients. Medical institutions are very concerned about IoT security because of the network enabled IoT devices' integration with healthcare network infrastructure.