Analysis of Android Malware Detection Techniques: A Systematic Review

Abstract

The emergence and rapid development in complexity and popularity of Android mobile phones has created proportionate destructive effects from the world of cyber-attack. Android based device platform is experiencing great threats from different attack angles such as DoS, Botnets, phishing, social engineering, malware and others. Among these threats, malware attacks on android phones has become a daily occurrence. This is due to the fact that Android has millions of user, high computational abilities, popularity, and other essential attributes. These factors influence cybercriminals (especially malware writers) to focus on Android for financial gain, political interest, and revenge. This calls for effective techniques that could detect these malicious applications on android devices. The aim of this paper is to provide a systematic review of the malware detection techniques used for android devices. The results show that most detection techniques are not very effective to detect zero-day malware and other variants that deploy obfuscation to evade detection. The critical appraisal of the study identified some of the limitations in the detection techniques that need improvement for better detection.

Machine Learning Algorithms Applied to System Security: A Systematic Review

“…The researches of [8] systematic survey on the researches that combine machine learning algorithm and data mining to cyber security Deep neural network and fuzzy logic are used to identify abnormality in network traffic [25]. A systematic survey was made by [31] on the techniques that are used for malware detection, while [32] used APIs and machine learning algorithm to detect malware in android.…”

Cybersecurity and Cyber Forensics: Machine Learning Approach Systematic Review

“…Hybrid system for traffic control and monitoring was implemented in [32] . A review was made by [40] on the methods that are used for malware detection, and [41] applied machine learning algorithm to detect malware in android mobile devices. In [42] they conducted a review on malware detection using parallel computing.…”

Android Permission Classifier: a deep learning algorithmic framework based on protection and threat levels

“…There are many Android malware sample dataset repositories such as DREDIN, 35 AndroZoo, 36 Genome project, 37 VirusShare 38 . Our framework performance was validated by series of experimental results using 6528 Android malware samples obtained from Ashawa and Sarah 25 . Effective permission extraction accuracy and classification based on the threat level of such permission request and the corresponding protection level was achieved by our model.…”

“…Different detections, classifications, and analysis techniques have been widely proposed by various researchers and security organizations across the world to curb the widespread of malware and to alleviate their attacks on Android devices. Some of the proposed techniques and strategies include dynamic detection, 5‐12 static detection, 13‐17 hybrid detection, 5,18‐22 and memory forensics techniques, 23‐31 respectively. The technique observes and monitors the application's behavior by focuses on knowing how the malware is connected and is interacting with mobile device resources at run time.…”