IoT malware detection using static and dynamic analysis techniques: A systematic literature review

Abstract

The Internet of Things (IoT) is reshaping the world with its potential to support new and evolving applications in areas, such as healthcare, automation, remote monitoring, and so on. This rapid popularity and growth of IoT‐based applications coincides with a significant surge in threats and malware attacks on IoT devices. Furthermore, the widespread usage of Linux‐based systems in IoT devices makes malware detection a challenging task. Researchers and practitioners have proposed a variety of techniques to address these threats in the IoT ecosystem. Both researchers and practitioners have proposed a range of techniques to counter these threats within the IoT ecosystem. However, despite the multitude of proposed techniques, there remains a notable absence of a comprehensive and systematic review assessing the efficacy of static and dynamic analysis methods in detecting IoT malware. This research work is a systematic literature review (SLR) that aims to offer a concise summary of the latest advancements in the field of IoT malware detection, specifically focusing on the utilization of static and dynamic analytic techniques. The SLR focuses on examining the present status of research, methodology, and trends in the area of IoT malware detection. It accomplishes this by synthesizing the findings from a wide range of scholarly works that have been published in well‐regarded academic journals and conferences. Additionally, the SLR highlights the significance of the empirical process that includes the role of selecting datasets, accurate feature selection and the utilization of machine learning algorithms in enhancing the detection accuracy. The study also evaluates the capability of different analysis techniques to detect malware and compares the performance of various models for IoT malware detection. Furthermore, the review concluded by addressing several open issues and challenges that the research community as a whole must address.