Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
The participatory sensing paradigm, through the growing availability of cheap sensors in mobile devices, enables applications of great social and business interest, e.g., electrosmog exposure measurement and early earthquake detection. However, users' privacy concerns regarding their activity traces need to be adequately addressed as well. The existing static privacy-enabling approaches, which hide or obfuscate data, offer some protection at the expense of data value. These approaches do not offer privacy guarantees and heterogeneous user privacy requirements cannot be met by them. In this paper, we propose a user-side privacy-protection scheme; it adaptively adjusts its parameters, in order to meet personalized location-privacy protection requirements against adversaries in a measurable manner. As proved by simulation experiments with artificial- and real-data traces, when feasible, our approach not only always satisfies personal location-privacy concerns, but also maximizes data utility (in terms of error, data availability, area coverage), as compared to static privacy-protection schemes.
Carmela González Troncoso, Bogdan Kulynych