SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks

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 o...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guangwu Hu, Bin Zhang, Xi Xiao, Weizhe Zhang, Long Liao, Ying Zhou, Xia Yan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	android machine learning static taint analysis dynamic taint analysis location privacy protection Science Q Astrophysics QB460-466 Physics QC1-999
Acceso en línea:	https://doaj.org/article/a59ad402148c4998bb7a63e93287ea21
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a59ad402148c4998bb7a63e93287ea21
record_format	dspace
spelling	oai:doaj.org-article:a59ad402148c4998bb7a63e93287ea212021-11-25T17:30:05ZSAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks10.3390/e231114891099-4300https://doaj.org/article/a59ad402148c4998bb7a63e93287ea212021-11-01T00:00:00Zhttps://www.mdpi.com/1099-4300/23/11/1489https://doaj.org/toc/1099-4300Insecure 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.Guangwu HuBin ZhangXi XiaoWeizhe ZhangLong LiaoYing ZhouXia YanMDPI AGarticleandroidmachine learningstatic taint analysisdynamic taint analysislocation privacy protectionScienceQAstrophysicsQB460-466PhysicsQC1-999ENEntropy, Vol 23, Iss 1489, p 1489 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	android machine learning static taint analysis dynamic taint analysis location privacy protection Science Q Astrophysics QB460-466 Physics QC1-999
spellingShingle	android machine learning static taint analysis dynamic taint analysis location privacy protection Science Q Astrophysics QB460-466 Physics QC1-999 Guangwu Hu Bin Zhang Xi Xiao Weizhe Zhang Long Liao Ying Zhou Xia Yan SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks
description	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.
format	article
author	Guangwu Hu Bin Zhang Xi Xiao Weizhe Zhang Long Liao Ying Zhou Xia Yan
author_facet	Guangwu Hu Bin Zhang Xi Xiao Weizhe Zhang Long Liao Ying Zhou Xia Yan
author_sort	Guangwu Hu
title	SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks
title_short	SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks
title_full	SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks
title_fullStr	SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks
title_full_unstemmed	SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks
title_sort	samldroid: a static taint analysis and machine learning combined high-accuracy method for identifying android apps with location privacy leakage risks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/a59ad402148c4998bb7a63e93287ea21
work_keys_str_mv	AT guangwuhu samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks AT binzhang samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks AT xixiao samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks AT weizhezhang samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks AT longliao samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks AT yingzhou samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks AT xiayan samldroidastatictaintanalysisandmachinelearningcombinedhighaccuracymethodforidentifyingandroidappswithlocationprivacyleakagerisks
_version_	1718412303602286592

SAMLDroid: A Static Taint Analysis and Machine Learning Combined High-Accuracy Method for Identifying Android Apps with Location Privacy Leakage Risks

Ejemplares similares