Patent · US Active

Privacy-preserving machine learning in the three-server model

US11222138B2 · kind B2 · utility

5Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 17, 2018
Grant dateJan 11, 2022
Priority date
Expiry dateJul 17, 2038

Classification

  • Technology area (CPC A)Human Necessities
  • CPC primaryA63B2244/10
  • WIPO fieldFurniture, games
  • WIPO sectorOther fields

Abstract

Methods and systems according to embodiments of the invention provide for a framework for privacy-preserving machine learning which can be used to obtain solutions for training linear regression, logistic regression and neural network models. Embodiments of the invention are in a three-server model, wherein data owners secret-share their data among three servers who train and evaluate models on the joint data using three-party computation (3PC). Embodiments of the invention provide for efficient conversions between arithmetic, binary, and Yao 3PC, as well as techniques for fixed-point multiplication and truncation of shared decimal values. Embodiments also provide customized protocols for evaluating polynomial piecewise functions and a three-party oblivious transfer protocol.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.