Computational Privacy Group

We are a research group at Imperial College London studying the privacy risks arising from large scale behavioral datasets. We develop attack models and design solutions to collect and use data safely.

Today people leave digital breadcrumbs wherever they go and whatever they do online and offline. This data dramatically increases our capacity to understand and affect the behaviour of individuals and collectives, has been key to recent advances in AI, but also raise fundamentally new privacy and fairness questions. The Computational Privacy Group aims to provide leadership, in the UK and beyond, in the safe, anonymous, and ethical use of large-scale behavioural datasets coming from the Internet of Things (IoT) devices, mobile phones, credit cards, browsers, etc.

Our projects have already demonstrated the limits of data anonymization (or de-identification) in effectively protecting the privacy of individuals in Big Data, the risk of inference in behavioral datasets coming from mobile phone, and developed solutions to allow individuals and companies to share data safely. While technical in nature, our work has had significant public policy implication for instance in reports of United Nations, FTC, and the European Commission as well as in briefs to the U.S. Supreme Court.

Research Areas

Identification Learning

We develop statistical and machine learning technique to uniquely identify individuals in large-scale behavioral datasets. These techniques show the limits of pseudonymization and anonymization in protecting people's privacy.

Safe Data Sharing

We build privacy-preserving and conscientious techniques to collect and use data while respecting people's privacy. For instance, we're building with MIT the OPAL (Open Algorithms) platform to safely share location data and openPDS to give individuals control over their data.

Societal impact of AI

Modern privacy is not only about controling the information but also the ability to control how this information is used e.g. for insurance pricing or ad-targeting. We study fairness in algorithmic-decision making and, more generally, the impact of AI on society.

News and Events

Selected publications

The full list of our papers is available on Google Scholar

Our Team

Yves-Alexandre de Montjoye

Group leader

Yves-Alexandre is an Assistant Professor at Imperial College London. He received his PhD from the MIT Media Lab and was a Postdoc at Harvard. He holds MScs in Applied Math from Louvain, Ecole Centrale Paris (Centralien), and KULeuven. View website - View bio

Thibaut
Lienart

Postdoc

Thibaut received his PhD in computational statistics from Oxford. Thibaut's research interests include the application of machine learning techniques on behavioral datasets for identification learning as well as adversarial machine learning.

Josiane
Dufour

MSc student

Josiane spent the last 3 years as a data analyst in industry after completing her BComm at McGill University. She is currently pursuing an MSc in Business Analytics at Imperial College London. Her research focuses on fairness and transparency in algorithmic decision-making.

Ali
Farzanehfar

PhD student

Ali has a MSc in high energy physics jointly from the University of Southampton and CERN. His research focuses on quantifying the privacy of human behavioral datasets, as well as studying the impact of AI algorithmic decision making on society.

Andrea
Gadotti

PhD student

Andrea received his MSc in mathematical logic from the University of Turin. His research interests include differential privacy, determining vulnerabilities in data-release systems, and designing privacy-preserving mechanims.

Florimond
Houssiau

PhD student

Florimond received his MSc in applied mathematics from UCLouvain. His research interests include obfuscation and privacy risks in Web search data .

Shubham
Jain

Research assistant

Shubham received his BTech from IIT Bombay. He was a founding member of Qure.ai, a startup developing deep learning solutions for the health sector. His research interests includes building secure and privacy enabling systems at scale.

Axel
Oehmichen

PhD student

Axel has masters in computer science from Imperial College London and ENSEEIHT (France). He worked for Societé Generale CIB. Axel leads the development of the OPAL project and is interested in privacy-preserving architectures.

Luc
Rocher

PhD student

Luc has a MSc in computer science from Ecole Normale Superieure de Lyon. His research focuses on re-identification, privacy and anonymity, as well as large-scale analysis of human behaviour.

Arnaud
Tournier

PhD student

Arnaud has masters in mathematics from Paris VI, Paris XI and from Ecole Centrale Paris. His research interests include biometrics and profiling.

Contact

Email:X@Y where X=demontjoye, Y=imperial.ac.uk.
Assistant (if urgent): Fay Miller, +44 20 7594 8612

We are located in the Data Science Institute in the William Penney Laboratory. The best entry point is via Exhibition road, through the Business school (see map below). From there, just take the stairs towards the outdoor court. Enter the outdoor corridor after the court and the institute will be on your right (please press the Data Science intercom button for access).

Please address mails to:
Department of Computing
Imperial College London
180 Queens Gate
London SW7 2AZ