Patent · US Active

Increasing security of neural networks by discretizing neural network inputs

US11354574B2 · kind B2 · utility

0Cited by
2References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 27, 2020
Grant dateJun 7, 2022
Priority date
Expiry dateApr 27, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/094
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for increasing the security of neural network by discretizing neural network inputs. One of the methods includes receiving a network input for a neural network; processing the network input using a discretization layer, wherein the discretization layer is configured to generate a discretized network input comprising a respective discretized vector for each of the numeric values in the network input; and processing the discretized network input using the plurality of additional neural network layers to generate a network output for the network input.

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