Comprehensive review on machine learning and deep learning techniques for malware detection in android and IoT devices

In recent times, IoT devices are being expeditiously integrated into our lives, while Android is expanding to become the most dominant mobile operating system in the market. With this growth comes the challenge of protecting these software and gadgets from being exploited by individuals or groups with malevolent intents. Malware has always been a rapidly evolving threat to the digital ecosystem, endangering its safety and security. As threat actors repeatedly find new ways to inject malware into our computer systems, traditional methods of detecting malware are becoming increasingly redundant. In response, new and emerging technologies such as machine learning and deep learning are being utilized to identify and mitigate the spread of malicious software. In this comprehensive review, we analyze and compare the extensive research dedicated to the development of machine and deep learning models for detecting malicious behavior in Android and IoT devices. Our contributions include a comprehensive literature review of surveys featuring machine learning (ML) and deep learning (DL) models for malware detection in IoT and Android devices. Additionally, we compare various ML and DL models proposed by researchers to gain valuable insights. Lastly, we examine different datasets used to train ML and DL models in addition to providing an up-to-date list of recently discovered IoT malware.