Detecting Malicious Android Applications Based On API calls and Permissions Using Machine learning Algorithms

Abstract

Android malware is growing, and the Android operating system is becoming more mainstream. Malware developers are using new strategies to build harmful Android apps, significantly weakening the capability of conventional malware detectors, which are unable to identify these mysterious malicious applications. Machine learning methods can be used to identify unknown Android malware using the functionality gleaned from static and dynamic reviews of Android apps. This article aims to compare and analyze different Android malware detection systems based on detection techniques, analysis processes, and extracted features. We learned scientific investigations in all Android malware detection approaches that use machine learning, demonstrating that machine learning algorithms are often used in this area to identify Malicious programs in the wild.