XGBoost-Based Android Malware Detection

Abstract

Malware remains the most significant security threat to smartphones in spite of the constantly upgrading of the system. In this paper, we introduce an Android malware detection method based on XGBoost model. We subsequently discuss the effect of feature selection on the classification. In the end, we verify the high efficacy and good accuracy of this model through the experiment, which achieves similar results to the SVM while spending less time.