A context-perceptual privacy protection approach on Android devices

Android applications (apps for short) frequently send users' personally identifiable data over IP networks. Previous attempts to address privacy leakage on mobiles by checking whether these sensitive data is off the device. Actually, some benign apps need to collect users' privacy information for many sensitive tasks (e.g., contacts manager, location service, or finance). Since these kinds of data transmissions provide an application's functionality, treating these as privacy leakages are false positives. In this paper, we present Android Privacy Assistant (APA), a practical privacy protection system that reveals privacy disclosure and provides fine-grained privacy information modifications to balance privacy and data usability. APA leverages machine learning to detect privacy leaks by inspecting network traffic, and uses generalization techniques to decrease privacy sensitivity. The evaluation result shows that APA can detect privacy leakage with up to 95% accuracy in our dataset and have almost no overhead on network and battery consumption.