Performance analysis of intrusion detection systems using the PyCaret machine learning library on the UNSW-NB15 dataset

Abstract

As one of the fastest growing technologies on earth, the Internet of Things (IoT) is being embraced almost everywhere. From smart home technology to industrial automation, IoT is revolutionizing almost everything around us. It has enabled humans and organizations to do more with less, both in terms of time, as well as - nances. This feat of the Internet of Things, however, has also led to an alarming rise in attacks on IoT networks. Among these attacks, botnet intrusions are perhaps the most worrying ones. And with the advancement of time and technology, attackers are getting more creative. Hence, it is important to use better and more e cient machine learning technologies to identify these attacks and detect these intrusions before they can paralyze the system. This research aims to identify a more e cient machine learning approach for detecting botnets in IoT networks by utilizing the Py- Caret machine learning library and analyzing its overall performance. The research will encompass di erent classi ers and analyze the di erent performance metrics for each of them. It will also shed light on the feasibility of using the PyCaret library and how well suited it is for such usage.