Probabilistic Prediction of Privacy Risks in User Search Histories

This paper proposes a new model of user-centric, global, probabilistic privacy, geared for today’s challenges of helping users to manage their privacy-sensitive information across a wide variety of social networks, online communities, QA fo-rums, and search histories. Our approach anticipates an adversary that harnesses global background knowledge and rich statistics in order to make educated guesses, that is, probabilistic inferences at sensitive data. We aim for a tool that simulates such a powerful adversary, predicts pri-vacy risks, and guides the user. In this paper, our frame-work is specialized for the case of Internet search histo-ries. We present preliminary experiments that demonstrate how estimators of global correlations among sensitive and non-sensitive key-value items can be fed into a probabilistic graphical model in order to compute meaningful measures of privacy risk