I am currently a PhD student in privacy-preserving ML under the supervision of Aurélien Bellet in Magnet team. My doctoral work explores how privacy guarantees are modified when learning is done in a fully decentralized fashion. I like this subject as it has major social impacts, and plays with beautiful mathematical tools: graphs, optimization, differential privacy. I was previously civil-servant for my studies at ENS Lyon in Computer Science. I graduated from a dual-degree programme as a civil engineer at MINES ParisTech. I have a Master’s of Research degree in applied mathematics for machine learning (MVA).

I am interested in the social impact of machine learning. I graduated from Master Degree of Philosophy at Paris 1 Panthéon Sorbonne. I did various projects for the popularization of science. Furthermore, I am particularly drawn to privacy, fairness, accountability and regulatory issues with regard to ML from a mathematical point of view.

As a woman in engineering, I am a firm believer in diversity and I strive to advocate at a personal level by volunteering in projects that promote girls and women in STEM industries. I participate to a lot of local actions, but currently I chose to focus on a big event: EGMO 2026 in France. The European Girls’ Mathematical Olympiad is an international mathematical contest of a very high level, aiming at encouraging girls to discover and explore their mathematical talent. If you are interested by sponsoring the event, please contact me!

Research interests

Among others topics, I am interested in:

• privacy-preserving Machine Learning
• federated and decentralized learning
• fair machine learning

How to prononce my name?

I don’t care if you have an unusual prononciation, and I am very bad at pronouncing foreign names. You can pronounce my first name as Harry pronounces his owl’s name in Harry Potter. For my last name, that’s the same prononciation “Il faut Cyffers” and “Il faut s’y faire” in French, and nearly the same “Cyffers” and “see fair”.