The revolution of smart devices such as smartphones, smart washing machines, smart cars is increasing every year, as these devices are provided connected with the network and provide the online functionality and services available with the lowest cost. In this context, the Android operating system (OS) is very popular due to its openness. It has major stakeholder in the smart devices but has also become an attractive target for cyber-criminals. This chapter presents a systematic and detailed survey of the malware detection mechanisms using deep learning and machine learning techniques. Also, it classifies the Android malware detection techniques in three main categories including static, dynamic, and hybrid analysis. The main contribution of this chapter are (1) It briefly describing the background and feature extraction of the static, dynamic, and hybrid analysis. (2) This chapter discusses the basic methodology and frameworks which classify, cluster, or extract Android malware features. (3) Exploring the dataset, harmful features, and classification results. (4) Discussing the current challenges and issues. Moreover, it discusses the most important factors, data-mining algorithms, and processed frameworks.
|Title of host publication||Malware Analysis Using Artificial Intelligence and Deep Learning|
|Editors||Mark Stamp, Mamoun Alazab, Andrii Shalaginov|
|Number of pages||42|
|Publication status||Published - 20 Dec 2020|