A Novel Android Malware Detection System: Adaption of Filter-Based Feature Selection Methods

Abstract

Android is the most preferred mobile operating system in the world. Applications are available from both official application repositories and other application stores. For these reasons, there has been a remarkable increase in malware for the Android operating system in recent years. In this study, a novel Android malware detection system is proposed by using filter-based feature selection methods. The proposed approach is static Android malware detection based on machine learning. Permissions extracted from application files are used as features in the developed system. Dimension reduction is carried out with eight different feature selection methods to enhance the running time and efficiency of machine learning algorithms. While four of these methods are used in Android malware detection systems, the remaining four methods are adapted from text classification studies. The adapted methods are compared in terms of both extracted features and classification results. When the results are examined, it is shown that the adapted methods improve the efficiency of the classification algorithms and can be used in this field.