A Literature Review on Android Mobile Malware Detection using Machine Learning Techniques

Abstract

In recent times very sophisticated and complicated malware are being produced on a regular basis and it has grown into one of the stealthiest and lethal attack techniques used against critical information technology infrastructures. In recent years, android is now the most expected smartphone operating system which is open source. However, Android's fast progress is impeded by the rising threat of Android malware, which uses Smartphones to carry out harmful acts. Malware uses a number of techniques to evade detection systems, posing new hurdles for reliable detection. The two main classifications for current Android malware detection approaches are signature-based detection and machine-learning-based detection. To address the limits of signature-based detection, researchers and antimalware firms have turned to a machine-learning-based detection approach. This review study disseminates present machine-learning-based Android malware detection techniques and compares them parametrically. As a result, the purpose of this review is to look at a variety of machine-learning-based detection methods as well as future possibilities in this domain.