Clémentine Gritti : Let Them Drop in Federated Learning (making it not a big deal!)

Vous pouvez consulter l’enregistrement de ce séminaire ici (durée : 1 heure).

Heure et date : le 11 juin 2025 à 12h30
Lieu : PK-1150 et Zoom
Conférencière : Clémentine Gritti
Titre : Let Them Drop in Federated Learning (making it not a big deal!)

Abstract : Secure model aggregation is nowadays recognized as the key component for Federated Learning (FL). It enables the collaborative training of a global machine learning model without leaking any information about FL clients’ local models. It is shown that clients who fail to complete the protocol, referred to as dropped clients, can seriously affect the correct computation of the global machine learning model. While the literature counts multiple fault-tolerant secure aggregation protocols, they rely on secret sharing techniques to reconstruct the inputs of dropped clients. As a consequence, the performance of these solutions decreases with increasing dropout rates. In this talk, we present recent fault-tolerant secure aggregation contributions, based on the combination of homomorphic encryption and secret sharing mechanisms, which only rely on the inputs of online clients. These contributions are agnostic to client failures and, therefore, outperform existing solutions.

Bio : Clémentine Gritti received her Ph.D. degree in computer science from the University of Wollongong, Australia, in 2017. She was a postdoctoral researcher at the Norwegian University of Science and Technology, Norway, and Eurecom, France. She was a lecturer at the University of Canterbury, New Zealand, from 2020 to 2023. She now is a professor junior at INSA Lyon, France. Her current research interests include designing public-key cryptographic protocols for security and privacy in various environments, such as Federated Learning, the Internet of Things, and blockchain technologies.