216 citations
- Office National d'Études et de Recherches AérospatialesFR3 papers
- Institut de Recherche pour le DéveloppementFR2 papers
- Université de ToulouseFR2 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR2 papers
- Université Paris-SaclayFR2 papers
- Acteurs, Ressources et Territoires dans le DéveloppementFR1 paper
- Astrophysique, Instrumentation et ModélisationFR1 paper
- CEA Paris-SaclayFR1 paper
- Centre de Physique ThéoriqueFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Centre National d'Études SpatialesFR1 paper
- Collège de FranceFR1 paper
5 papers
Carpet-bombing patch: attacking a deep network without usual requirements
Pol Labarbarie, Adrien Chan-Hon-Tong, Stéphane Herbin +1
Although deep networks have shown vulnerability to evasion attacks, such attacks have usually unrealistic requirements. Recent literature discussed the possibility to remove or not…
Out-Of-Distribution Detection Is Not All You Need
Joris Guérin, Kevin Delmas, Raul Sena Ferreira +1
The usage of deep neural networks in safety-critical systems is limited by our ability to guarantee their correct behavior. Runtime monitors are components aiming to identify unsaf…
MICROSCOPE mission: final results of the test of the Equivalence Principle
Pierre Touboul, Gilles Métris, Manuel Rodrigues +44
The MICROSCOPE mission was designed to test the Weak Equivalence Principle (WEP), stating the equality between the inertial and the gravitational masses, with a precision of $10^{-…
HDDL 2.1: Towards Defining an HTN Formalism with Time
D. Pellier, H. Fiorino, M. Grand +2
Real world applications of planning, like in industry and robotics, require modelling rich and diverse scenarios. Their resolution usually requires coordinated and concurrent actio…
Learning "best" kernels from data in Gaussian process regression. With application to aerodynamics
Jean-Luc Akian, Luc Bonnet, Houman Owhadi +1
This paper introduces algorithms to select/design kernels in Gaussian process regression/kriging surrogate modeling techniques. We adopt the setting of kernel method solutions in a…