Exploring Privacy Leakage from the Resource Usage Patterns of Mobile Apps

Due to the popularity of smart phones and mobile apps, a potential privacy risk with the usage of mobile apps is that, from the usage information of mobile apps (e.g., how many hours a user plays mobile games in each day), private information about a user’s living habits and personal activities can be inferred. To assess this risk, this thesis answers the following research question: can the type of a mobile app (e.g., email, web browsing, mobile game, music streaming, etc.) used by a user be inferred from the resource (e.g., CPU, memory, network, etc.) usage patterns of the mobile app? This thesis answers this question for two kinds of systems, a single mobile device and a mobile cloud computing system. First, two privacy attacks under the same framework are proposed based on supervised learning algorithms. Then these attacks are implemented and explored in a mobile device and in a cloud computing environment. Experimental evaluations show that the type of app can be inferred with high probability. In particular, the attacks achieve up to 100% accuracy on a mobile device, and 66.7% accuracy in the mobile cloud computing environment. This study shows that resource usage patterns of mobile apps can be used to infer the type of apps being used, and thus can cause privacy leakage if not protected.