IoT Anomaly Detection Using a Multitude of Machine Learning Algorithms

Abstract

The security of IoT (Internet of Things) systems is crucial yet challenging. Anomaly detection can help assess and improve the security of these devices and systems. The detection of anomalous traffic can be performed with the use of machine learning algorithms. Gradient Boosting is a Machine Learning (ML) technique that handles both regression and classification problems and uses decision tree algorithms to produce a prediction model. eXtreme Gradient Boosting (XGBoost) is a unique implementation of Gradient Boosting that has shown very good performance and outcomes in various problems. In this paper, XGBoost’s classification abilities are examined when applied to the adopted IoT-23 dataset to see how well anomalies can be identified and what type of anomaly exists in IoT systems. Moreover, the results obtained from XGBoost are compared to other ML methods including Support Vector Machines (SVM) and Deep Convolutional Neural Networks (DCNN). The classification results were assessed based on accuracy, precision, recall, and various other performance metrics. Our experimental results showed that XGBoost outperformed both SVM and DCNN achieving accuracies up to 99.98%. In addition, XGBoost proved to be the most efficient method with respect to execution time.