Patent · US Active

Neural network watermarking

US12373520B2 · kind B2 · utility

0Cited by
6References
23Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 1, 2020
Grant dateJul 29, 2025
Priority date
Expiry dateSep 30, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Training a neural network and embedding a watermark in the network to prove ownership. The network includes a plurality of trainable parameters associated with network nodes in which the plurality of trainable parameters is split into a first set of trainable parameters and a second set of trainable parameters. A first set of training samples is input to the network and the network is trained by iterating the first set of samples through the network to update the first set of parameters and hindering the second set of parameters to be updated during iteration of the first set of samples. A second set of samples is input and the watermark is embedded by iterating the second set of samples through the network to update the second set of parameters and hindering the first set of parameters to be updated during iteration of the second set of samples.

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