IEEE

SAMK: Secure Aggregation for Federated Learning Under Multiple Keys With Low Communication ...

Abstract: While multi-key homomorphic encryption (MKHE) ensures privacy in federated learning (FL) by encrypting model updates, its requirement for aggregate ...
IEEE

Exploring Communication-Efficient Federated Learning via Stateless in-Network Aggregation

Abstract: As an ambitious training paradigm, federated learning has garnered increasing attention in recent years, which enables collaborative training of a global model without accessing users’ ...