MVIIDroid: A Multiple View Information Integration Approach for Android Malware Detection and Family Identification

Abstract

With the rapid growth of Android applications, there is an urgent need for powerful Android malware detection technology nowadays. Existing classification models can be summarized with the following two steps-feature extraction and classification model learning. To further enhance the representation ability of existing classification models, this article presents an Android malicious application detection framework termed multiview information integration technology (MVIIDroid). To be specific, in our approach, we extract applications’ multiple components, transform them into embedding feature vectors and train a multiple Kernel learning model as the classifier. To illustrate the effectiveness of our model, we evaluate MVIIDroid on two Android malware datasets of 6820 malware and 6820 benign applications. Results show that we have superior classification performances when separating malware from benign applications. Moreover, we further evaluate MVIIDroid's ability to attribute malicious applications to their actual families. The experimental results well demonstrate the effectiveness of the proposed model.