Android malware detection and identification frameworks by leveraging the machine and deep learning techniques: A comprehensive review

Abstract

The ever-increasing growth of online services and smart connectivity of devices have posed the threat of malware to computer system, android-based smart phones, Internet of Things (IoT)-based systems. The anti-malware software plays an important role in order to safeguard the system resources, data and information against these malware attacks. Nowadays, malware writers used advanced techniques like obfuscation, packing, encoding and encryption to hide the malicious activities. Because of these advanced techniques of malware evasion, traditional malware detection system unable to detect new variants of malware. Cyber security has attracted many researchers in the past for designing of Machine Learning (ML) or Deep Learning (DL) based malware detection models. In this study, we present a comprehensive review of the literature on malware detection approaches. The overall literature of the malware detection is grouped into three categories such as review of feature selection (FS) techniques proposed for malware detection, review of ML-based techniques proposed for malware detection and review of DL-based techniques proposed for malware detection. Based on literature review, we have identified the shortcoming and research gaps along with some future directives to design of an efficient malware detection and identification framework.