PD-ML-Lite: Private Distributed Machine Learning from Lightweight Cryptography

DOI10.1007/978-3-030-30215-3_8MaRDI QIDQ6488968zbMATH OpenFDO

Authors Malik Magdon-Ismail, Muhammad Ishaq, Vassilis Zikas

Publication date 14 March 2024

Full work available at URL https://doi.org/10.1007/978-3-030-30215-3_8

Mathematics Subject Classification ID

Privacy of data (68P27) Modes of computation (nondeterministic, parallel, interactive, probabilistic, etc.) (68Q10) Learning and adaptive systems in artificial intelligence (68T05) Cryptography (94A60)

Recommendations

• Differentially Private Distributed Learning
• ML confidential: machine learning on encrypted data
• Client-aided privacy-preserving machine learning
• Privacy-preserving distributed machine learning based on secret sharing
• SPEED: secure, private, and efficient deep learning

Cites work

• A distributed and incremental SVD algorithm for agglomerative data analysis on large networks
• Fast projection onto the simplex and the l₁ ball
• Hierarchical ALS Algorithms for Nonnegative Matrix and 3D Tensor Factorization
• scientific article; zbMATH DE number 1049353 (Why is no real title available?)
• On the complexity of nonnegative matrix factorization
• Projected Gradient Methods for Nonnegative Matrix Factorization
• Successive nonnegative projection algorithm for robust nonnegative blind source separation
• SVD based initialization: A head start for nonnegative matrix factorization
• Testing Statistical Hypotheses of Equivalence and Noninferiority
• The algorithmic foundations of differential privacy

Cited in

(2)

• Privacy-preserving decentralised singular value decomposition
• Client-aided privacy-preserving machine learning

This page was built for publication: PD-ML-Lite: Private Distributed Machine Learning from Lightweight Cryptography

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6488968)