An accurate, scalable and verifiable protocol for federated differentially private averaging

DOI10.1007/s10994-022-06267-9arXiv2006.07218OpenAlexW3199781406MaRDI QIDQ6097108

Aurélien Bellet, Jan Ramon, César Sabater

Publication date: 12 June 2023

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.07218

zbMATH Keywords

robustnessprivacydifferential privacyfederated learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the connectivity of random m-orientable graphs and digraphs
• Distributed differential privacy via shuffling
• Extremal Mechanisms for Local Differential Privacy
• Optimal Lower Bound for Differentially Private Multi-party Aggregation
• Embedding Spanning Trees in Random Graphs
• What Can We Learn Privately?
• The Algorithmic Foundations of Differential Privacy
• Sponge-Based Pseudo-Random Number Generators
• Our Data, Ourselves: Privacy Via Distributed Noise Generation
• The Knowledge Complexity of Interactive Proof Systems
• Coin flipping by telephone a protocol for solving impossible problems
• Proving in Zero-Knowledge that a Number is the Product of Two Safe Primes
• Privacy-Preserving Stream Aggregation with Fault Tolerance
• How Not to Prove Yourself: Pitfalls of the Fiat-Shamir Heuristic and Applications to Helios
• Differential Privacy on Finite Computers
• Advances and Open Problems in Federated Learning
• Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity
• On the Connectivity of Sensor Networks Under Random Pairwise Key Predistribution
• Brief Announcement
• Differential Privacy

This page was built for publication: An accurate, scalable and verifiable protocol for federated differentially private averaging