3 papers
cs.DC2026
Privacy-Preserving Federated Averaging with Byzantine Aggregators in Asynchronous Networks
Antonella Del Pozzo, Achille Desreumaux, Mathieu Gestin +2
Federated Learning requires secure aggregation to prevent gradient leakage, yet existing protocols suffer from key limitations: they assume synchrony, require heavy peer-to-peer co…
cs.CR2024
Secret Quorums: Protecting Byzantine Protocols Against Adaptive Adversaries
Maxence Perion, Sara Tucci-Piergiovanni, Rida Bazzi
Modern committee-based payment protocols improve scalability by delegating critical operations to small subsets of participants, such as validator committees in blockchains or shar…
cs.CR2024
Fantastyc: Blockchain-based Federated Learning Made Secure and Practical
William Boitier, Antonella Del Pozzo, Álvaro García-Pérez +9
Federated Learning is a decentralized framework that enables multiple clients to collaboratively train a machine learning model under the orchestration of a central server without…