Systematic Approach for Malware Detection in IoT Devices: Enhancing Security and Performance

The proliferation of Internet of Things (IoT) devices has introduced significant security challenges, particularly concerning the detection and mitigation of malware threats. This study presents a systematic approach to malware detection that aims to improve both the security and performance of IoT systems. Using the IoT23 dataset, which contains a wide range of network traffic patterns from various IoT devices and malware families, the research explores and evaluates multiple machine learning techniques. These include ensemble methods such as Bagging, Stacking, Voting, AdaBoost, and H2O AutoML, as well as advanced models such as sparse neural networks with pruning and feature selection and regularized classifiers L1. The primary objective is to develop lightweight yet highly accurate models suitable for deployment on resource-constrained IoT devices. A comprehensive comparison of these techniques demonstrates the importance of achieving a balance between detection accuracy and computational efficiency. Among the models evaluated, the SNIPE approach shows the best performance, achieving an accuracy of 91.9% while maintaining minimal computational overhead. This makes it particularly well suited for real-world IoT environments, where performance and energy efficiency are critical. The findings of this study provide valuable insights for the development of robust, scalable, and resource-aware malware detection systems, laying a strong foundation for future research and practical cybersecurity solutions in the rapidly evolving IoT landscape.