MALWARE ANALYSIS ON THE UNSW_NB15 DATASET

The Internet of Things (IoT) is one of the latest advancements in the Internet. It is defined as a network of connected physical and digital devices and sensors that generate and exchange large amounts of data without human intervention. By eliminating the need for human operators, the IoT can process more data than ever before, faster, and more efficiently. This article focuses on IoT network security by investigating the usefulness of machine learning algorithms for detecting anomalies in IoT network data. It examines Machine Learning (ML) algorithms successfully used in relatively similar situations and compares them using several settings and methods. This article implements the following algorithms: Random Forest (RF), Naive Bayes (NB), Multi-Layer Perceptron (MLP), a variant of the artificial neural network algorithm class, Support Vector Machine (SVM), and AdaBoost (ADA) on the UNSW_NB15 dataset. The best results were obtained by the Random Forest algorithm, with an accuracy of 99.3%.