Post-Doctoral Research Visit F/M Tailored PRivacy via Interpretable Mobility Behavioral exposure (PRISM)

The Inria Saclay-Île-de-France Research Centre was established in 2008. It has developed as part of the Saclay site in partnership with Paris-Saclay University and with the Institut Polytechnique de Paris .

The centre has 41 project teams , 27 of which operate jointly with Paris-Saclay University and the Institut Polytechnique de Paris; Its activities occupy over 600 people, scientists and research and innovation support staff, including 44 different nationalities.

Every year Inria International Relations Department has a few postdoctoral positions in order to support Inria international collaborations.

The postdoctoral contract will have a duration of 12 to 24 months. The default start date is November 1st, 2026 and not later than January, 1st 2027. The postdoctoral fellow will be recruited by one of the Inria Centres in France but it is recommended that the time is shared between France and the partner’s country (please note that the postdoctoral fellow has to start his/her contract being in France and that the visits have to respect Inria rules for missions).

This postdoctoral position is proposed within the TRiBE research team at Inria Saclay and focuses on advancing privacy-preserving mobility analytics through interpretable behavioral modeling.

Mobility is a defining human behavior and an increasingly traceable signal in today’s digital ecosystem. It underpins data-driven decision-making and fuels the expanding mobile services market (projected to reach $463 billion by 2032). However, the exploitation of mobility data raises significant privacy concerns. Persistent routines and timedependent social behaviors make individual mobility traces highly distinctive, increasing the risk of privacy exposure. While existing privacy-preserving techniques reduce re-identification risks, they typically apply uniform protection, overlooking individual behavioral differences and often degrading data utility. In practice, privacy exposure varies substantially across users and is strongly influenced by behavioral traits, as shown in our previous work [hal-05057826v1]. This motivates the need for adaptive privacy-preserving mechanisms that account for individual exposure levels, enabling tailored protection while preserving the utility of mobility-driven services. 

PRISM aims to develop tailored privacy-preserving techniques by leveraging interpretable behavioral exposure modeling. Building on prior work [hal-05288506v1], the project will quantify exposure across multiple dimensions to characterize individual privacy risk. This interpretability will guide the design of adaptive protection mechanisms, both AI-based and non-AI-based, while preserving mobility-driven services and supporting privacy-aware, perceptive Internet edge networks. The datasets to be used in this research proposal will consist of publicly available cellular datasets (e.g., Shenzhen CDRs) and other non-public datasets to which the team has signed NDAs (e.g., Shanghai CDR).

Candidates for postdoctoral positions are recruited after the completion of their Ph.D. or a first postdoctoral period. To be eligible, candidates must have defended their Ph.D. no later than December 31, 2023.

In order to encourage mobility, the postdoctoral position must take place in a scientific environment that is truly different from the one of the Ph.D. (and, if applicable, from the position held since the Ph.D.); particular attention is thus paid to French or international candidates who obtained their doctorate abroad.

The objective of the PRISM project is to design tailored privacy-preserving mechanisms based on interpretable modeling of mobility behavioral exposure.

The postdoctoral researcher will:

• Develop models to quantify individual behavioral exposure across multiple mobility dimensions
• Investigate how behavioral traits influence privacy risks
• Design adaptive protection mechanisms (AI-based and non-AI-based)
• Evaluate the trade-off between privacy protection and data utility

The work will combine data-driven modeling, privacy analysis, and interpretable machine learning, with a strong focus on reproducibility and real-world applicability.

• Handling and characterization of publicly available cellular datasets (e.g., Shenzhen)
• Modeling behavioral exposure in mobility data
• Designing interpretable privacy risk metrics
• Developing adaptive privacy-preserving mechanisms
• Conducting large-scale experimental evaluations
• Publishing results in top-tier venues

• Strong background in machine learning, data science, or networking
• Experience with mobility data or spatiotemporal analysis is a plus
• Interest in privacy, data protection, or trustworthy AI
• Good programming skills (Python, data analysis frameworks)
• Ability to work in an international research environment

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage

€2,788 gross per month