I am a postdoctoral researcher in AI safety at the University of Luxembourg. My work sits at the intersection of machine learning reliability, formal and statistical verification, and robust evaluation.
Publications
CV
Contact
About me
I am a postdoctoral researcher at the University of Luxembourg, where I am part of the Security, Reasoning and Validation (SeRVal) team within the Security and Trust (SnT) interdisciplinary research centre. Before that, I graduated with a PhD in computer science from the University of Rennes in April 2024, after 3 years of doctoral study spent within Inria’s LinkMedia team and in Thales Group’s La Ruche team.
Research
My research is focused on AI Safety, with a particular emphasis on formal and statistical verification methods.
The subject of my Ph.D. thesis was the estimation of the reliability of deep neural network predictions using rare-event simulation algorithms.
My current interests include:
- reliability and robustness estimation for machine learning systems,
- uncertainty-aware evaluation,
- verification-oriented tools for high-stakes AI,
- mathematically grounded explanations of machine learning behavior.
Contact me
You can contact me at the institutional address below: