Patent · US Active

Differential privacy dataset generation using generative models

US11847538B2 · kind B2 · utility

1Cited by
2References
28Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 11, 2021
Grant dateDec 19, 2023
Priority date
Expiry dateMay 26, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V20/56
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Apparatuses, systems, and techniques to train a generative model based at least in part on a private dataset. In at least one embodiment, the generative model is trained based at least in part on a differentially private Sinkhorn algorithm, for example, using backpropagation with gradient descent to determine a gradient of a set of parameters of the generative models and modifying the set of parameters based at least in part on the gradient.

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