Android malware detection applying feature selection techniques and machine learning

作     者：Keyvanpour, Mohammad Reza Shirzad, Mehrnoush Barani Heydarian, Farideh 

作者机构：Alzahra Univ Fac Engn Dept Comp Engn Tehran Iran Alzahra Univ Fac Engn Dept Comp Engn Data Min Lab Tehran Iran 

出 版 物：《MULTIMEDIA TOOLS AND APPLICATIONS》 (多媒体工具和应用)

年 卷 期：2023年第82卷第6期

页      面：9517-9531页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Android operating system Malware detection Machine learning Random forest Feature selection 

摘      要：Android operating system is known as one of the most popular mobile operating systems. The malware intrusion increases in the same pace as the production of applicable software. Propagation of new and transformed malware in seconds is a critical challenge in malware detection. Android software supplies thousands of features, providing assistance to identify malware applications. In this paper, a novel method based on a random forest algorithm, which applied three different feature selection techniques is proposed. This paper assesses the consequence of applying three different feature selection types including effective, high weight and effective group feature selection. Experiments conducted on Drebin dataset indicate applying the feature selection methods ameliorate the accuracy in terms of metrics and required time. In addition, comparison between the candidate feature selection model and a variety of algorithms as baselines proves the merit of applying feature selection on Random Forest, which outperforms other models based on several metrics.