Members
Overall Objectives
Research Program
Application Domains
Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Dissemination
Bibliography
XML PDF e-pub
PDF e-Pub


Section: Software and Platforms

Privacy

GEPETO (GEoPrivacy-Enhancing TOolkit) is an open source software for managing location data (currently in development in cooperation with LAAS). GEPETO can be used to visualize, sanitize, perform inference attacks and measure the utility of a particular geolocated dataset. For each of these actions, a set of different techniques and algorithms can be applied. The global objective of GEPETO is to enable a user to design, tune, experiment and evaluate various sanitization algorithms and inference attacks as well as visualizing the following results and evaluating the resulting trade-off between privacy and utility. An engineer (Izabela Moïse) has contributed to the development of a distributed version of GEPETO based on the MapReduce paradigm and the Hadoop framework that is able to analyze datasets composed of millions of mobility traces in a few minutes [30] .

GNOME (Geoprivacy eNhancing tOol for MobilE) is an application for Android smartphone whose main objectives are to (1) to help the user to understand which type of personal information can be learnt from his mobility traces through inference attacks as well as (2) to allow him to decide if he want to sanitize his location data before it is released to a third party (for instance this data could be perturbed according to the desired level of privacy of the user). In addition of the inference attacks such as the extraction of the points of interests and the construction of the mobility model, different mechanisms for generating fake yet realistic mobility traces have been implemented. In particular, one of this method leverages on the mobility model learnt while the second one perturbs the location based on a location variant of differential privacy, a well-established privacy model. These fake mobility traces, that are hard to distinguish from real ones, can be fed to applications running on the smartphone instead of his real location upon request of the user. This application is actually available as a beta release and experiments are actually being conducted with real users in order to test the functionalities of the application. This application has been developed by David Lanoë, an engineer hired as part of the "security and privacy for location-based services" EIT ICT labs activity.