Internet of Things (IoT) Intrusion Detection by Machine Learning (ML): A Review

Iman Farhadian Dehkordi, Kooroush Manochehri, Vahe Aghazarian
dx.doi.org/10.17576/apjitm-2023-1201-02

Abstract

One of today's fastest-growing technologies is the Internet of Things (IoT). It is a technology that lets billions of smart devices or objects known as "Things" collect different kinds of data about themselves and their surroundings utilizing different sensors. For example, it could be used to keep an eye on and regulate industrial services, or it could be used to improve corporate operations. But the IoT currently faces more security threats than ever before. This review paper discusses the many sorts of cybersecurity attacks that may be used against IoT devices. Also, K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), and Artificial Neural Network (ANN) are examples of Machine Learning (ML) approaches that can be employed in IDS. The goal of this study is to show the results of analyzing various classification algorithms in terms of confusion matrix, accuracy, precision, specificity, sensitivity, and f-score to Develop an Intrusion Detection System (IDS) model.

keyword

Dataset, Internet of Things (IoT), Intrusion Detection System (IDS), IoT attacks, Machine Learning (ML)

Area

Cyber Security and Digital Forensic