Android Malware Detection with Contrasting Permission Patterns

作     者：XIONG Ping WANG Xiaofeng NIU Wenjia ZHU Tianqing LI Gang 

作者机构：School of Information and Security Engineering Zhongnan University of Economics and Law Wuhan 430073 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Information Engineering Technology Chinese Academy of Sciences Beijing 100093 China School of Information Technology Deakin University Melbourne VIC 3125 Australia Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin 541004 China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2014年第11卷第8期

页      面：1-14页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 081202[工学-计算机软件与理论] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported by Deakin Cyber Security Research Cluster National Natural Science Foundation of China under Grant Nos. 61304067 and 61202211 Guangxi Key Laboratory of Trusted Software No. kx201325 the Fundamental Research Funds for the Central Universities under Grant No 31541311314 

主　　题：malware detection permissionpattern classification contrast set Android 

摘      要：As the risk of malware is sharply increasing in Android platform,Android malware detection has become an important research *** works have demonstrated that required permissions of Android applications are valuable for malware analysis,but how to exploit those permission patterns for malware detection remains an open *** this paper,we introduce the contrasting permission patterns to characterize the essential differences between malwares and clean applications from the permission aspect Then a framework based on contrasting permission patterns is presented for Android malware *** to the proposed framework,an ensemble classifier,Enclamald,is further developed to detect whether an application is potentially *** contrasting permission pattern is acting as a weak classifier in Enclamald,and the weighted predictions of involved weak classifiers are aggregated to the final *** on real-world applications validate that the proposed Enclamald classifier outperforms commonly used classifiers for Android Malware Detection.