System and method with masking for certified defenses against adversarial patches
US12400006B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 9, 2023 |
| Grant date | Aug 26, 2025 |
| Priority date | — |
| Expiry date | Nov 6, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F2221/033
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A computer-implemented system and method relate to certified robust defenses against adversarial patches. A set of one-mask images are generated using a source image and a first mask at a set of predetermined image regions. The set of predetermined image regions collectively cover at least every pixel of the source image. A particular one-mask image with a highest prediction loss is selected from among the set of one-mask images. A set of two-mask images is generated using the selected one-mask image and a second mask at the set of predetermined image regions. A particular two-mask image with a highest prediction loss is selected from among the set of two-mask images. The machine learning system is trained using a training dataset, which includes the selected two-mask image.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.