A framework with randomized encoding for a fast privacy preserving calculation of non-linear kernels for machine learning applications in precision medicine

DOI10.1007/978-3-030-31578-8_27zbMATH Open1437.68154OpenAlexW2980220314MaRDI QIDQ3297645FDOQ3297645

Authors: Ali Burak Ünal, Mete Akgün, Nico Pfeifer 

Publication date: 20 July 2020

Published in: Cryptology and Network Security (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-030-31578-8_27

Recommendations

• Privacy-preserving linear and nonlinear approximation via linear programming
• Differentially private empirical risk minimization
• Private computation on encrypted genomic data
• Privacy-preserving ridge regression on distributed data
• Towards a practical cluster analysis over encrypted data

zbMATH Keywords

precision medicinestring kernelrandomized encodingprivacy-preserving machine learningRBF kernel

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Medical applications (general) (92C50) Privacy of data (68P27)

Cites Work

• Support-vector networks
• Computationally private randomizing polynomials and their applications
• Cryptography in $NC^0$
• Garbled circuits as randomized encodings of functions: a primer
• How to garble arithmetic circuits
• Algorithms in HElib

Uses Software

• HElib
• geno2pheno
• Kinship-Privacy

This page was built for publication: A framework with randomized encoding for a fast privacy preserving calculation of non-linear kernels for machine learning applications in precision medicine

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3297645)