Free for All! Assessing User Data Exposure to Advertising Libraries on Android

摘要: In this work, we systematically explore the potential reach of advertising libraries through these channels. We design a framework called Pluto that can be leveraged to analyze an app and discover whether it exposes targeted user data—such as contact information, interests, demographics, medical conditions so on—-to opportunistic ad library. present prototype implementation Pluto, embodies novel strategies for using natural language processing illustrate what data potentially learned from network files inputs. also leverages machine learning mining models reveal networks learn list installed apps. validate with collection apps which have determined ground truth about they may reveal, together set derived survey conducted gives corresponding lists 300 users. use show hence networks, achieve 75% recall 80% precision selected coming inputs, even better results certain based on is first tool estimates risk associated integrating in four available channels arbitrary sets data.