Accéder directement au contenu

Julien Girard-Satabin

6
Documents
Identifiants chercheurs

Présentation

I am a research engineer at CEA LIST, Saclay. My main research interests are in the broad sense trustworthy AI. I made my thesis on the topic of formal verification of deep neural networks, trying to ease formal verification using abstract interpretation, Satisfaction Modulo Theory and Linear Programming. I am currently working on developping techniques and tools to ease the verification of neural networks. I am also interested in the impact of machine learning on our societies, and I will be eager to work with people on this area.

Publications

Image document

Caractériser des propriétés de confiance d'IA avec Why3

Julien Girard-Satabin , Michele Alberti , François Bobot , Zakaria Chihani
JFLA 2023 - 34èmes Journées Francophones des Langages Applicatifs, Jan 2023, Praz-sur-Arly, France. pp.291--295
Communication dans un congrès hal-03936881v1
Image document

CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustness

Julien Girard-Satabin , Michele Alberti , François Bobot , Zakaria Chihani , Augustin Lemesle
AISafety, Jul 2022, Vienne, Austria
Communication dans un congrès hal-03687211v2
Image document

Partitionnement en régions linéaires pour la vérification formelle de réseaux de neurones

Julien Girard-Satabin , Aymeric Varasse , Guillaume Charpiat , Zakaria Chihani , Marc Schoenauer
Journées Francophones des Langages Applicatifs, Apr 2021, Saint Médard d’Excideuil, France
Communication dans un congrès hal-03127853v1
Image document

CAMUS: A Framework to Build Formal Specifications for Deep Perception Systems Using Simulators

Julien Girard-Satabin , Guillaume Charpiat , Zakaria Chihani , Marc Schoenauer
ECAI 2020 - 24th European Conference on Artificial Intelligence, Jun 2020, Santiago de Compostela, Spain
Communication dans un congrès hal-02440520v1