SPEED: secure, private, and efficient deep learning

DOI10.1007/s10994-021-05970-3zbMath1489.68090arXiv2006.09475OpenAlexW3036496141MaRDI QIDQ2051270

Cédric Gouy-Pailler, Arnaud Grivet Sébert, Martin Zuber, Rafaël Pinot, Renaud Sirdey

Publication date: 24 November 2021

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

Full work available at URL: https://arxiv.org/abs/2006.09475

zbMATH Keywords

homomorphic encryptiondata protectioncollaborative learningdistributed differential privacy

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Privacy of data (68P27)

Related Items

\textsf{ComBo}: a novel functional bootstrapping method for efficient evaluation of nonlinear functions in the encrypted domain

Uses Software

• MNIST
• PySyft
• Gazelle

Cites Work

• Unnamed Item
• Faster homomorphic encryption is not enough: improved heuristic for multiplicative depth minimization of Boolean circuits
• Extremal Mechanisms for Local Differential Privacy
• (Leveled) fully homomorphic encryption without bootstrapping
• Faster Fully Homomorphic Encryption: Bootstrapping in Less Than 0.1 Seconds
• What Can We Learn Privately?
• The Algorithmic Foundations of Differential Privacy
• Our Data, Ourselves: Privacy Via Distributed Noise Generation
• Privacy-Preserving Stream Aggregation with Fault Tolerance
• ML Confidential: Machine Learning on Encrypted Data
• Advances in Cryptology - CRYPTO 2003