Profile picture for Florent Guepin

Florent Guepin

Email: florent.guepin@imperial.ac.uk

My name is Florent and I’m a second-year PhD candidate in the CPG working on the privacy of machine learning-based systems. More specifically, I study the robustness of these systems against inference attacks such as Property Inference and Attribute Inference.

Before starting my PhD, I obtained an MSc in Fundamental Computer Science from ENS Lyon, France, and the Diplôme d’Ingénieur de l’école Centrale de Lyon (equivalent to a Bachelors and Master’s degree) from Centrale Lyon, France.

Before joining the CPG, I did an internship at Oxford University, under the supervision of James Ben Worrell and at Orange Research under the supervision of Loïc Ferrera. The first internship focused on verification, studying both the existential fragment of Büchi arithmetic and of linear arithmetic over p-adic fields and the other on applied cryptography, attacks against quantum systems.


News


Publications

  • Guépin, F., Meeus, M., Cretu, A.-M., and de Montjoye Y. A. Synthetic is all you need: removing the auxiliary data assumption for membership inference attacks against synthetic data. 18th DPM International Workshop on Data Privacy Management, Sept 2023, The Hague (2023).
  • Meeus, M., Guépin, F., Cretu, A.-M., and de Montjoye Y. A. Achilles’ Heels: Vulnerable Record Identification in Synthetic Data Publishing. 28th European Symposium on Research in Computer Security (ESORICS), Sept 2023, The Hague (2023).