155 citations
- Université de BourgogneFR41 papers
- Centre National de la Recherche ScientifiqueFR18 papers
- Mohammed V UniversityMA7 papers
- École PolytechniqueFR3 papers
- Laboratoire d'Informatique de BourgogneFR3 papers
- Sorbonne UniversitéFR3 papers
- Université Bourgogne Franche-ComtéFR3 papers
- University of Applied Sciences MainzDE3 papers
- Arts et MétiersFR2 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR2 papers
- Franche-Comté Électronique Mécanique Thermique et Optique - Sciences et TechnologiesFR2 papers
- Indian Institute of Information Technology Design and Manufacturing JabalpurIN2 papers
75 papers
Few Edges Are Enough: Few-Shot Network Attack Detection with Graph Neural Networks
Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha +1
Detecting cyberattacks using Graph Neural Networks (GNNs) has seen promising results recently. Most of the state-of-the-art models that leverage these techniques require labeled ex…
Greedy Gray Codes for some Restricted Classes of Binary Words
Nathanaël Hassler, Vincent Vajnovszki, Dennis Wong
We investigate the existence of greedy Gray codes, based on the choice of the first element in the code, for two classes of binary words: generalized Fibonacci words and generalize…
MiSuRe is all you need to explain your image segmentation
Syed Nouman Hasany, Fabrice Mériaudeau, Caroline Petitjean
The last decade of computer vision has been dominated by Deep Learning architectures, thanks to their unparalleled success. Their performance, however, often comes at the cost of e…
Queuing dynamics of asynchronous Federated Learning
Louis Leconte, Matthieu Jonckheere, Sergey Samsonov +1
We study asynchronous federated learning mechanisms with nodes having potentially different computational speeds. In such an environment, each node is allowed to work on models wit…
FAVANO: Federated AVeraging with Asynchronous NOdes
Louis Leconte, Van Minh Nguyen, Eric Moulines
In this paper, we propose a novel centralized Asynchronous Federated Learning (FL) framework, FAVANO, for training Deep Neural Networks (DNNs) in resource-constrained environments.…
A Survey on Malware Detection with Graph Representation Learning
Tristan Bilot, Nour El Madhoun, Khaldoun Al Agha +1
Malware detection has become a major concern due to the increasing number and complexity of malware. Traditional detection methods based on signatures and heuristics are used for m…