A GAF and CNN based Wi-Fi Network Intrusion Detection System

Abstract

Wi-Fi networks have become ubiquitous nowadays in enterprise and home networks creating opportunities for attackers to target them. These attackers exploit various vulnerabilities in Wi-Fi networks to gain unauthorized access to networks or extract data from end users' devices. A network intrusion detection system (NIDS) is deployed to detect these attacks before they can cause any significant damages to the network's functionalities or security. In this work, we propose a deep learning based NIDS using a 2D convolutional neural network (CNN) to detect intrusions inside a Wi-Fi network. Wi-Fi frames are transformed into images using Gramian Angular Field (GAF) technique. These images are then fed to the proposed deep learning based NIDS for intrusion detection. We used a benchmark Wi-Fi intrusion datasets, AWID3, for our model development. Our proposed model is able to achieve an accuracy and f-measure of 99.77% and 99.66%, respectively.