A Hybrid Intrusion Detection Model for Identification of Threats in Internet of Things Environment

Internet of Things (IoT) has transcended from its application in traditional sensing networks such as wireless and radio frequency identification to life-changing critical applications. However, IoT are still vulnerable threats, attacks, intrusions, other malicious activities. Intrusion Detection Systems (IDS) that employ unsupervised learning techniques used secure sensitive data transmitted on preserve privacy. This paper proposes a hybrid model for intrusion detection relies dimension reduction algorithm, an classifier. The proposed employs Principal Component Analysis (PCA) reduce the number features dataset. K-means algorithm generates clusters serve class labels Support Vector Machine (SVM) Experimental results using NSL-KDD UNSW-NB15 datasets justify effectiveness our detecting activities networks. model, when trained, identifies benign behaviours unlabelled