Files
Download Full Text (5.3 MB)
Abstract
In the current Android architecture, users have to decide whether an app is safe to use or not by themselves. Savvy users can make correct decisions to avoid unnecessary privacy breaches, however most users are not capable or do not care to make impactful decisions. To assist those users, we propose DroidNet, an Android permission control framework based on crowdsourcing. In this framework, DroidNet runs new apps and their permissions initially, and then collects data based on each individual user’s settings in regards to each permission unique to every installed app. After collecting each user’s data, DroidNet provides recommendations on whether to accept or reject the permission requests based on decisions from peer expert users.
To seek expert users, we utilize an expertise ranking algorithm using a transitional Bayesian inference model. The recommendation, respective to each application permission, is based on the aggregated expert responses and our generated confidence level, which are collectively stored and sorted in our DroidNet database. The overall culmination of the model resulted in the creation of a real-time Android application which utilizes our Bayesian inference model and aggregate data from each individual user, all of which is connected to our DroidNet database.
Publication Date
2017
Keywords
DroidNet, Android, Framework, Application, Crowdsourcing, Permissions
Disciplines
Computer Engineering | Engineering
Faculty Advisor/Mentor
Carol Fung
VCU Capstone Design Expo Posters
Rights
© The Author(s)
Date of Submission
May 2018