Communication Dans Un Congrès Année : 2025

SAAFL: Secure Aggregation for Label-Aware Federated Learning

Résumé

Secure aggregation (SA) has emerged as a vital component of federated learning (FL), enabling collaborative training of a global machine learning model while safeguarding the privacy of clients' local datasets. Most existing SA protocols implement the privacy preservingvariant of federated averaging (FedAvg) as the aggregation technique and assume independent and identically distributed (IID) datasets across clients. This assumption makes FedAvg unsuitable for non-IID scenarios, where variations in client datasets lead to less effective global model. We propose SAAFL, a SA protocol specifically designed for non-IID settings and more specifically for the recently proposed federated label-aware aggregation (FedLA) protocol. SAAFL computes the weighted average of clients' inputs where weights depend on the label distributions and should remain confidential. SAAFL is resilient to client dropouts and supports client selection. Our experimental results show that it achieves comparable model accuracy with FedLA and remains efficient in terms of computation and communication.

Fichier principal
Vignette du fichier
publi-8204.pdf (1.69 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05066911 , version 1 (14-05-2025)

Licence

Identifiants

  • HAL Id : hal-05066911 , version 1

Citer

Aftab Akram, Harry N H Pham, Melek Önen, Clémentine Gritti. SAAFL: Secure Aggregation for Label-Aware Federated Learning. IFIP SEC 2025 - 40th International Conference on ICT Systems Security and Privacy Protection, IFIP, May 2025, Maribor, Slovenia. pp.1-14. ⟨hal-05066911⟩
299 Consultations
177 Téléchargements

Partager

  • More