Patent · US Active

System and method for machine learning architecture with adversarial attack defense

US11520899B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 17, 2019
Grant dateDec 6, 2022
Priority date
Expiry dateOct 6, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2221/033
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A platform for training deep neural networks using push-to-corner preprocessing and adversarial training. A training engine adds a preprocessing layer before the input data is fed into a deep neural network at the input layer, for pushing the input data further to the corner of its domain.

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