An Android Malware Detection Approach Based on Static Feature Analysis Using Machine Learning Algorithms

In the past decade, mobile devices became necessary for modern civilization and contributed directly to its development stages in defining mobile information access. Nonetheless, along with these rapid developments in modern mobile devices, security issues rise dramatically, and malware is the most concerning of all. Therefore, many studies and research are still trending in this spectrum, using Machine Learning approaches to prevent and reduce malware's impact. This paper seeks to add to what is already a foundation of various malware detection efforts by presenting a static base classification approach for malware detection based on android permissions and API calls. This approach is based on three well-known Machine Learning algorithms, Support Vector Machines (SVM), K-nearest neighbors (KNN), and Naive Bayes (NB) against a comprehensive new Android malware dataset (CICInvesAndMal2019), in pursuit of achieving high malware detection rates and contribution to the efforts and studies in protecting the development of mobile information. access.