Autoencoder-based Malware Analysis: An Imagery Analysis Approach to Enhance the Security of Smart City IoT

Abstract. Smart Cities, the modern digital urban landscapes, are primarily facilitated by the Internet of Things (IoT) infrastructures for information communication. Despite Smart Cities' benefits, risks revolving around data privacy and security within the IoT sphere raise concern. Particularly, malware attacks significantly threaten IoT systems, demanding proactive research into malware prevention techniques. This paper presents a study on autoencoder (AE)-based methodologies for efficient imagery analysis-based malware classification, aiming to enhance the Smart Cities IoT security. It focuses on effective malware classification utilizing various AE structures applied to grayscale or RGB malware derived images, contributing to improved malware detection and analysis. We conduct experiments with different input shapes and multi-label classification output to ascertain the robustness and generalizability of the proposed method. By analysing the classification capabilities of different AE types, we prove that variational AE built with convolutional neural network can achieve effective malware imagery classification in Smart City IoT environments.