Patent · US Active

Methods for secure learning of parameters of a convolution neural network, and for secure input data classification

US11003991B2 · kind B2 · utility

1Cited by
1References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 2, 2017
Grant dateMay 11, 2021
Priority date
Expiry dateMar 12, 2040

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L9/008
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for secure learning of parameters of a convolution neural network, CNN, for data classification includes the implementation, by data processing of a first server, including receiving from a second server a base of already classified learning data, the learning data being homomorphically encrypted; learning in the encrypted domain, from the learning database, the parameters of a reference CNN including a non-linear layer (POLYNOMIAL) operating an at least two-degree polynomial function approximating an activation function; a batch normalization layer before each non-linear layer (POLYNOMIAL); and transmitting the learnt parameters to the second server, for decryption and use for classification.

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