节点文献

Android权限异常检测技术的研究

Android authority anomaly detection technology

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 崔学成陆南

【Author】 CUI Xue-cheng;LU Nan;School of Electronic Information,Jiangsu University of Science and Technology;

【机构】 江苏科技大学电子信息学院

【摘要】 在Android系统中,权限机制是系统重要的组成部分,往往权限的申请一定程度上会反应出该应用的具体目的。而一个应用要想顺利和正常工作是离不开权限的,所以用权限来判断一个应用的恶意性是具有可行性的。并且一个恶意应用要想对用户的隐私造成威胁是需要多个权限联合起来一起运作的,单个权限并不能对用户的财产安全造成损害。为了能较为准确地判断恶意应用,文中先通过卡方检验去除冗余权限,然后通过FP-growth算法挖掘权限之间的关联性,构建FP-tree,建立检测模型,来对应用进行恶意性判决。通过大量实验设置最优最小支持度,最后实验结果表明,文中提出的方法比其他检测方法得出的结果更为准确。文中首次将加权FP-growth算法和卡方检验应用到移动端,结果表明西方提出的方法具备可行性。

【Abstract】 In the Android system,the authority mechanism is an important part of the system,the authority is often the right to respond to the specific purpose of the application.And an application to be successful and normal work is inseparable from the authority,so the use of authority to determine the feasibility of a malicious application is feasible.And a malicious application to want to pose a threat to the user’s privacy is the need to work together to jointly operate a single authority and can not cause damage to the user’s property security.In order to accurately judge the malicious application,this paper first through the chi square test removes redundant permissions,and then through the FP-growth algorithm for mining association,construction of power between FP-tree,a detection model for malicious application of judgment.Through a large number of experiments,the optimal minimum support is set up,and the experimental results show that the method proposed is more accurate than other methods.Weighted FP-growth algorithm and chi square test were applied to mobile terminal for the first time,and the results show that it is feasible.

  • 【文献出处】 信息技术 ,Information Technology , 编辑部邮箱 ,2017年12期
  • 【分类号】TP309;TP316
  • 【被引频次】3
  • 【下载频次】61
节点文献中: 

本文链接的文献网络图示:

本文的引文网络