基于PPR的Android恶意软件检测方法

Android malware detection method based on PPR

为有效提高Android恶意软件的检测效率,突破现有方法大多针对单一权限或特定组合权限且对于权限之间的相互关联性研究较少的局限性,提出一种基于权限佩奇排序(PPR)方法的Android恶意软件检测方法。从恶意软件申请的权限中构造特征权限,建立关联系数矩阵;针对权限之间的相互关联性,通过PPR方法量化特征权限的权限比重;构建特征权限矩阵检测未知的恶意软件。实验结果验证了该方法的可行性,其能够有效提高Android恶意软件的检测效率,从数值关系角度为Android恶意软件的检测提供了新的思路。

To effectively improve the efficiency of Android malware detection,break through the limitations that existing methods mostly concern about single permission or specific combination of permissions and are careless about the relationships of permissions,an Android malware detection method based on permission PageRank（PPR）method was proposed.Characteristic permissions were extracted from all permissions applied by the malware and correlation coefficient matrix was established.Characteristic permissions＇ proportions were quantified via PPR method based on the correlations of permissions and structured characteristic permissions matrix to detect unknown malware.This method provides a new way for the detection of Android malware from the perspective of numerical relationship,and the experiment verifies the feasibility of this method,it can effectively improve the detection efficiency of Android malware.