5 papers
Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization
Aurélien Bellet, Edwige Cyffers, Davide Frey +3
Decentralized Learning (DL) enables users to collaboratively train models without sharing raw data by iteratively averaging local updates with neighbors in a network graph. This se…
Context Adaptive Cooperation
Timothé Albouy, Davide Frey, Mathieu Gestin +2
As shown by Reliable Broadcast and Consensus, cooperation among a set of independent computing entities (sequential processes) is a central issue in distributed computing. Consider…
Low-Cost Privacy-Preserving Decentralized Learning
Sayan Biswas, Davide Frey, Romaric Gaudel +5
Decentralized learning (DL) is an emerging paradigm of collaborative machine learning that enables nodes in a network to train models collectively without sharing their raw data or…
Asynchronous BFT Asset Transfer: Quasi-Anonymous, Light, and Consensus-Free
Timothé Albouy, Emmanuelle Anceaume, Davide Frey +4
This paper introduces a new asynchronous Byzantine-tolerant asset transfer system (cryptocurrency) with three noteworthy properties: quasi-anonymity, lightness, and consensus-freed…
Near-Optimal Communication Byzantine Reliable Broadcast under a Message Adversary
Timothé Albouy, Davide Frey, Ran Gelles +5
We address the problem of Reliable Broadcast in asynchronous message-passing systems with nodes, of which up to are malicious (faulty), in addition to a message adversary t…