Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Vujasinovic, Milos"'
Decentralized learning (DL) faces increased vulnerability to privacy breaches due to sophisticated attacks on machine learning (ML) models. Secure aggregation is a computationally efficient cryptographic technique that enables multiple parties to com
Externí odkaz:
http://arxiv.org/abs/2405.07708
Autor:
Dhasade, Akash, Kermarrec, Anne-Marie, Pires, Rafael, Sharma, Rishi, Vujasinovic, Milos, Wigger, Jeffrey
Publikováno v:
2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS 2023)
Decentralized learning (DL) systems have been gaining popularity because they avoid raw data sharing by communicating only model parameters, hence preserving data confidentiality. However, the large size of deep neural networks poses a significant ch
Externí odkaz:
http://arxiv.org/abs/2306.04377
Publikováno v:
2023 3rd European Workshop on Machine Learning and Systems (EuroMLSys 2023)
Decentralized learning (DL) has gained prominence for its potential benefits in terms of scalability, privacy, and fault tolerance. It consists of many nodes that coordinate without a central server and exchange millions of parameters in the inherent
Externí odkaz:
http://arxiv.org/abs/2304.08322
Autor:
Vujasinovic, Milos
In this report, we address the issue of scalability of the existing secure aggregation protocols used in decentralized machine learning to a very high number of nodes. As a solution, we propose a novel decentralized aggregation protocol that can be p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______185::cd1b067183bf06d6035306fc152cf50a
https://infoscience.epfl.ch/record/286909
https://infoscience.epfl.ch/record/286909