典型文献
Android Malware Detection Method Based on Permission Complement and API Calls
文献摘要：
The dynamic code loading mechanism of the Android system allows an application to load execut-able files externally at runtime.This mechanism makes the development of applications more convenient,but it also brings security issues.Applications that hide mali-cious behavior in the external file by dynamic code load-ing are becoming a new challenge for Android malware detection.To overcome this challenge,based on dynamic code loading mechanisms,three types of threat models,i.e.Model Ⅰ,Model Ⅱ,and Model Ⅲ are defined.For the Model Ⅰ type malware,its malicious behavior occurs in DexCode,so the application programming interface(API)classes were used to characterize the behavior of the Dex-Code file.For the Model Ⅱ type and Model Ⅲ type mal-wares whose malicious behaviors occur in an external file,the permission complement is defined to characterize the behaviors of the external file.Based on permission com-plement and API calls,an Android malicious application detection method is proposed,of which feature sets are constructed by improving a feature selection method.Five datasets containing 15,581 samples are used to evaluate the performance of the proposed method.The experi-mental results show that our detection method achieves accuracy of 99.885％on general dataset,and performes the best on all evaluation metrics on all datasets in all com-parison methods.
文献关键词：
中图分类号：
作者姓名：
YANG Jiyun;TANG Jiang;YAN Ran;XIANG Tao
作者机构：
College of Computer Science,Chongqing University,Chongqing 400044,China
文献出处：
引用格式：
[1]YANG Jiyun;TANG Jiang;YAN Ran;XIANG Tao-.Android Malware Detection Method Based on Permission Complement and API Calls)[J].电子学报（英文）,2022(04):773-785
A类：
Permission,execut,cious,DexCode,wares,performes
B类：
Android,Malware,Detection,Method,Based,Complement,API,Calls,dynamic,code,loading,system,allows,able,files,externally,runtime,This,makes,development,applications,more,convenient,but,also,brings,security,issues,Applications,that,hide,by,becoming,new,challenge,malware,detection,To,overcome,this,mechanisms,three,types,threat,models,Model,defined,For,its,malicious,occurs,programming,interface,classes,were,used,characterize,whose,behaviors,permission,complement,calls,proposed,which,feature,constructed,improving,selection,Five,datasets,containing,samples,evaluate,performance,experi,mental,results,show,our,achieves,accuracy,general,best,evaluation,metrics,parison,methods
AB值：
0.442357
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
