Applying Wide & Deep Learning Model for Android Malware Classification

作     者：Le Duc Thuan Pham Van Huong Hoang Van Hiep Nguyen Kim Khanh 

作者机构：Ha Noi University of Science and TechnologyHa Noi100000Viet Nam Academy of Cryptography TechniquesHa Noi100000Viet Nam 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第45卷第6期

页      面：2741-2759页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0839[工学-网络空间安全] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 081201[工学-计算机系统结构] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 081202[工学-计算机软件与理论] 

主　　题：Wide and deep(W&D)learning convolutional neural network image feature raw features generalized features 

摘      要：Android malware has exploded in popularity in recent years,due to the platform’s dominance of the mobile *** the advancement of deep learning technology,numerous deep learning-based works have been proposed for the classification of Android *** learning technology is designed to handle a large amount of raw and continuous data,such as image content ***,it is incompatible with discrete features,i.e.,features gathered from multiple ***,if the feature set is already well-extracted and sparsely distributed,this technology is less effective than traditional machine *** the other hand,a wide learning model can expand the feature set to enhance the classification *** maximize the benefits of both methods,this study proposes combining the components of deep learning based on multi-branch CNNs(Convolutional Network Neural)with wide learning *** feature set is evaluated and dynamically partitioned according to its meaning and generalizability to subsets when used as input to the model’s wide or deep *** proposed model,partition,and feature set quality are all evaluated using the K-fold cross validation method on a composite dataset with three types of features:API,permission,and raw *** accuracy with Wide and Deep CNN(WDCNN)model is 98.64%,improved by 1.38%compared to RNN(Recurrent Neural Network)model.