Welcome to the InfoSci Platform
Reference Hub6
Privacy Rating of Mobile Applications Based on Crowdsourcing and Machine Learning

Privacy Rating of Mobile Applications Based on Crowdsourcing and Machine Learning

Bin Pan, Hongxia Guo, Xing You, Li Xu
Copyright: © 2022 |Volume: 30 |Issue: 3 |Pages: 15
ISSN: 1062-7375|EISSN: 1533-7995|EISBN13: 9781799897279|DOI: 10.4018/JGIM.20220701.oa5
Cite Article Cite Article

MLA

Pan, Bin, et al. "Privacy Rating of Mobile Applications Based on Crowdsourcing and Machine Learning." JGIM vol.30, no.3 2022: pp.1-15. http://doi.org/10.4018/JGIM.20220701.oa5

APA

Pan, B., Guo, H., You, X., & Xu, L. (2022). Privacy Rating of Mobile Applications Based on Crowdsourcing and Machine Learning. Journal of Global Information Management (JGIM), 30(3), 1-15. http://doi.org/10.4018/JGIM.20220701.oa5

Chicago

Pan, Bin, et al. "Privacy Rating of Mobile Applications Based on Crowdsourcing and Machine Learning," Journal of Global Information Management (JGIM) 30, no.3: 1-15. http://doi.org/10.4018/JGIM.20220701.oa5

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

With the advent of the 5G network era, the convenience of mobile smartphones has become increasingly prominent, the use of mobile applications has become wider and wider, and the number of mobile applications. However, the privacy of mobile applications and the security of users' privacy information are worrying. This article aims to study the ratings of data and machine learning on the privacy security of mobile applications, and uses the experiments in this article to conduct data collection, data analysis, and summary research. This paper experimentally establishes a machine learning model to realize the prediction of privacy scores of Android applications. The establishment of this model is based on the intent of using sensitive permissions in the application and related metadata. It is to create a regression function that can implement the mapping of applications to score . Experimental data shows that the feature vector prediction model can uniquely be used to represent the actual usage and scheme of a system's specific permissions for the application.