New Results on Permission Based Static Analysis for Android Malware

Abstract

Mobile devices' hardware have been enhancing day by day. With this development, mobile phones are supporting many programs and everyone takes advantage of them. Nevertheless, malware applications are increasing more and more so that people can come across lots of problems. Android is a mobile operating system that is the most used on the smart mobile phones. Because it is the most used and open source, it has been the target of attackers. Android security related to the permissions allowed by users to the applications. There have been many studies on the permission based Android malware detection. In this study, permission based Android malware system is analyzed. Unlike other studies, we propose permission weight approach. Each of permissions is given a different score by means of this approach. Then, K-nearest Neighbor (KNN) and Naive Bayes (NB) algorithms are applied and the proposed method is compared with the previous studies. According to the experimental results, the proposed approach has better results than the other ones.