SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks.
SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks.
复制标题
DOI：
10.3390/e23111489
复制
发表时间：
2021-11-10
期刊：
影响因子：
--
通讯作者：
Yan X
中科院分区：
文献类型：
--
作者：
Hu G;Zhang B;Xiao X;Zhang W;Liao L;Zhou Y;Yan X
不安全的应用程序(APP)越来越多地被用来窃取用户的位置信息用于非法目的，这在最近几年引起了高度关注。虽然现有的静态和动态污点分析方法对于识别这类主要依靠静态分析源代码或动态监测位置数据流的应用程序已经显示出很大的优势，但由于分析结果包含一定的漏报或真阴率，识别精度仍在研究中。为了提高可疑应用审查过程中的准确率，降低误判率，提出了一种静态代码分析和机器学习相结合的识别位置隐私泄露的Android应用的方法SAMLDroid，与现有方法相比，能有效提高识别率。SAMLDroid首先使用静态分析来仔细审查源代码，以调查具有位置获取意图的应用程序。然后，它利用训练有素的分类器，集成应用程序的多种功能来动态分析模式，并对应用程序的属性做出最终裁决。最后通过实验证明，SAMLDroid的准确率达到98.4%，比Apparecium高出近20%。
Insecure applications (apps) are increasingly used to steal users’ location information for illegal purposes, which has aroused great concern in recent years. Although the existing methods, i.e., static and dynamic taint analysis, have shown great merit for identifying such apps, which mainly rely on statically analyzing source code or dynamically monitoring the location data flow, identification accuracy is still under research, since the analysis results contain a certain false positive or true negative rate. In order to improve the accuracy and reduce the misjudging rate in the process of vetting suspicious apps, this paper proposes SAMLDroid, a combined method of static code analysis and machine learning for identifying Android apps with location privacy leakage, which can effectively improve the identification rate compared with existing methods. SAMLDroid first uses static analysis to scrutinize source code to investigate apps with location acquiring intentions. Then it exploits a well-trained classifier and integrates an app’s multiple features to dynamically analyze the pattern and deliver the final verdict about the app’s property. Finally, it is proved by conducting experiments, that the accuracy rate of SAMLDroid is up to 98.4%, which is nearly 20% higher than Apparecium.
登录
查看更多内容
DOI：
10.1109/tifs.2016.2646641
发表时间：
2017-05-01
影响因子：
6.8
作者：
Sun, Mingshen;Li, Xiaolei;Liang, Zhenkai
通讯作者：
Liang, Zhenkai
影响因子：
1.5
作者：
Enck, William;Gilbert, Peter;Sheth, Anmol N.
通讯作者：
Sheth, Anmol N.
DOI：
10.1109/tdsc.2016.2536605
发表时间：
2018-01-01
影响因子：
7.3
作者：
Saracino, Andrea;Sgandurra, Daniele;Martinelli, Fabio
通讯作者：
Martinelli, Fabio
DOI：
10.1142/s0218488502001648
发表时间：
2002-10-01
影响因子：
1.5
作者：
Sweeney, L
通讯作者：
Sweeney, L
影响因子：
--
作者：
Arzt, Steven;Rasthofer, Siegfried;McDaniel, Patrick
通讯作者：
McDaniel, Patrick