Integrating Machine Learning and Deep Learning Approaches for Efficient Malware Detection in IoT-Based Smart Cities

Abstract

Smart cities have gained popularity because they promise to address some of the biggest challenges facing urban areas today, such as: traffic congestion, air pollution, energy consumption, waste management, and public safety. A comprehensive study is conducted to enhance the malware detection performance in smart cities by integrating machine learning and IoT-based approaches with deep learning. The study aims to address future challenges in malware detection and improve the effectiveness of strategies used in smart cities. Machine learning algorithms are applied to analyze and classify models’ performance, enhancing computation time and categorial attacks. Deep learning techniques are commended to improve the accuracy and efficiency of malware detection in smart cities. The integration of IoT-based approaches and deep learning enables the detection of various types of malwares in smart cities. The study emphasizes the need for continuous research and development to enhance the performance of malware detection methods in the dynamic ecosystem of smart cities. The dataset was developed in a Unix/Linux-based virtual machine for classification purposes and is safe to use with malware software for Android devices based on the characteristics of the observations. 35 features and 100,000 observation data make up the data set. The results show promising results in terms of detecting malware in smart cities IoT devices.