Malware Detection on Android Smartphones using API Class and Machine Learning

This paper proposes a (new) method to detect malware in Android smartphones using API (application programming interface) classes. We use machine learning to classify whether an application is benign or malware. Furthermore, we compare classification precision rate from machine learning. This research uses 51 APIs package classes from 16 APIs classes and employs cross validation and percentage split test to classify benign and malware using Random Forest, J48, and Support Vector Machine algorithms. We use 412 total application samples (205 benign, 207 malware). We obtain that the classification precision average is 91.9%.