A New Android Malicious Application Detection Method Using Feature Importance Score

With the rapid development of the Internet and mobile terminals, there are a lot of important information stored in mobile phones. One important way to ensure that these information is not compromised is to detect and process malicious applications in mobile phones. In this paper, we describe a new android malicious application detection method using feature importance score. The model extracts the permissions, sensitive apis and some others of the Android application as features, which are filtered and optimized by the model. The random forest algorithm is selected as a classifier to effectively classify malicious applications and normal applications. The experimental results show that the proposed model has higher detection accuracy.