PriWe: Recommendation for Privacy Settings of Mobile Apps Based on Crowdsourced Users´ Expectations

Privacy is a pivotal issue of mobile apps because there is a plethora of personal and sensitive information in smartphones. Various mechanisms and tools are proposed to detect and mitigate privacy leaks. However, they rarely consider users´ preferences and expectations. Users hold various expectations towards different mobile apps. For example, users can allow a social app to access their photos rather than a game app because it is beyond users´ expectation when an entertainment app gets the personal photos. Therefore, we believe it is vital to understand users´ privacy expectations to various mobile apps and help them to mitigate privacy risks in the smartphone accordingly. To achieve this objective, we propose and implement PriWe, a system based on crowd sourcing driven by users who contribute privacy permission settings of their apps in smartphones. PriWe leverages the crowd sourced permission settings to understand users´ privacy expectation and provides app specific recommendations to mitigate information leakage. We deployed PriWe in the real world for evaluation. According to the feedbacks of 78 users from the real world and 382 participants from Amazon Mechanical Turk, PriWe can make proper recommendations which can meet participants´ privacy expectation and are mostly accepted by users, thereby help them to mitigate privacy disclosure in smartphones.