Platform for preventing adversarial attacks on image-based machine learning models
US10839265B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 12, 2018 |
| Grant date | Nov 17, 2020 |
| Priority date | — |
| Expiry date | Aug 6, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and computer-readable storage media for receiving a set of training images and a set of classification labels, generating a set of target codebooks based on the set of classification labels, the set of target codebooks being provided as a first set of vectors of random value and dimension, generating a set of output codebooks based on the set of training images, the set of output codebooks being provided as a second set of vectors of random value and dimension, training a ML model by minimizing a loss function provided as a mean-squared-error (MSE) loss function, the loss function being measured by the Euclidean distance between an output codebook of the set of output codebooks and a target codebook of the set of target codebooks.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.