Paper 2019/425

Homomorphic Training of 30,000 Logistic Regression Models

Flavio Bergamaschi, Shai Halevi, Tzipora T. Halevi, and Hamish Hunt

Abstract

In this work, we demonstrate the use the CKKS homomorphic encryption scheme to train a large number of logistic regression models simultaneously, as needed to run a genome-wide association study (GWAS) on encrypted data. Our implementation can train more than 30,000 models (each with four features) in about 20 minutes. To that end, we rely on a similar iterative Nesterov procedure to what was used by Kim, Song, Kim, Lee, and Cheon to train a single model [KSKLC18]. We adapt this method to train many models simultaneously using the SIMD capabilities of the CKKS scheme. We also performed a thorough validation of this iterative method and evaluated its suitability both as a generic method for computing logistic regression models, and specifically for GWAS.

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Published elsewhere. MINOR revision.ACNS 2019
DOI
10.1007/978-3-030-21568-2_29
Keywords
Approximate numbersHomomorphic encryptionGWASImplementationLogistic regression
Contact author(s)
thalevi @ nyu edu
flavio @ uk ibm com
History
2019-08-19: revised
2019-04-27: received
See all versions
Short URL
https://ia.cr/2019/425
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2019/425,
      author = {Flavio Bergamaschi and Shai Halevi and Tzipora T.  Halevi and Hamish Hunt},
      title = {Homomorphic Training of 30,000 Logistic Regression Models},
      howpublished = {Cryptology ePrint Archive, Paper 2019/425},
      year = {2019},
      doi = {10.1007/978-3-030-21568-2_29},
      note = {\url{https://eprint.iacr.org/2019/425}},
      url = {https://eprint.iacr.org/2019/425}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.