Motivation
In the era of digital health technologies, including health apps, wearable devices, and electronic health records, there is a significant amount of health-related data being collected that includes or can be associated with geographic information. Such data can be incredibly useful for personalized healthcare, offering tailored health advice, monitoring, and treatment options based on an individual's specific location-based environmental exposures, activities, or access to healthcare services.
However, the collection, storage, and analysis of georeferenced health data raise substantial privacy concerns. There is a risk that such information could be misused if it falls into the wrong hands, leading to potential privacy invasions, discrimination, or other forms of harm. "Geoprivacy for Personalized Health" thus encompasses the technologies, practices, and policies designed to protect individuals' location privacy while enabling the benefits of personalized health services.
The objective of this workshop is to bring together experts in public health, privacy, geographic information science, and related disciplines to discuss the challenges we are currently facing at this research nexus. This will include indepth discussions on topics including data anonymization techniques, secure data storage and transmission protocols, consent mechanisms, and regulations that govern the use of personal location data in healthcare contexts. We anticipate this workshop resulting in the foundations of a coauthored policy/white paper and/or research vision paper.
This is the first of two workshops jointly funded by the Government of Québec and the Luxembourg National Research Fund. The second workshop is scheduled to take place in Luxembourg in 2025.
Broad Objective
From a long-term perspective, we are building a robust collaboration network dedicated to geoprivacy-preserving personal health research, where members can access a diverse pool of complementary expertise (e.g., knowledge in encryption techniques, federated learning, or mobility behaviours) and resources (e.g., data from personal health projects). We particularly welcome computationally minded researchers and health experts who have run projects collecting personal location and health data. This is ultimately to conduct more collaborative, large-scale, and impactful personal health studies across various countries, enabled by geoprivacy preservation techniques.
Keynote
Speaker: Sébastien Gambs
Université du Québec à Montréal (UQAM)
Canada Research Chair (Tier 2) in Privacy-preserving and Ethical Analysis of Big Data
Title: Re-identification attacks on location data
Abstract:
Mobility data has proven to be of crucial importance in many domains, such as in city planning by enabling the understanding of global movement patterns and optimizing transportation infrastructures as well as by offering to public health authorities the means to study the spread of diseases, identify areas with higher exposure risk and monitor the effectiveness of public health interventions. However, among all the types of personal data, learning the location of an individual is one of the greatest threats against privacy. In particular, an inference attack, can use the mobility data of a user (together with some auxiliary information) to deduce the points of interests characterizing his mobility thus leading to detailed profiling, to predict his past, current and future locations or even to identify his social network. In this talk, I will focus in particular on reviewing re-identification attacks on location data, ranging from old approaches that leverage the use of mobility profiles to recent ones that leverage transformer neural network architectures to improve the accuracy of the re-identification. I will also discuss possible countermeasures to mitigate the success of such attacks as well as promising alternatives for the privacy-preserving sharing of mobility data.
Biography:
Sébastien Gambs currently holds the Canada Research Chair (Tier 2) in Privacy-preserving and Ethical Analysis of Big Data since December 2017. He joined the Computer Science Department of the Université du Québec à Montréal (UQAM) in January 2016, after having held a joint Research chair in Security of Information Systems between Université de Rennes 1 and Inria from September 2009 to December 2015. Before that, Sébastien was a CNRS postdoctoral researcher in LAAS-CNRS collaborating with Yves Deswarte on the concept of the "privacy-preserving identity card", after having defending in 2008 my PhD thesis in computer science at the Université de Montréal under the supervision of Gilles Brassard. He have defended in June 2014 his HDR (Habilitation à Diriger les Recherches) titled “Protection of Privacy in the Information Society“. As a part of his sabbatical, from January to May 2023 he was a visiting professor in the SPICY team in the IRISA laboratory (Rennes, France) after having been a visiting professor at the Systopia lab from the University of British Columbia (UBC) from July to December 2022. Sébastien is a member of the LATECE laboratory as well as the SERENE RISC cybersecurity network.