Digital watermarking of machine learning models
US11972408B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 21, 2019 |
| Grant date | Apr 30, 2024 |
| Priority date | — |
| Expiry date | Dec 17, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/82
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method may include embedding, in a hidden layer and/or an output layer of a first machine learning model, a first digital watermark. The first digital watermark may correspond to input samples altering the low probabilistic regions of an activation map associated with the hidden layer of the first machine learning model. Alternatively, the first digital watermark may correspond to input samples rarely encountered by the first machine learning model. The first digital watermark may be embedded in the first machine learning model by at least training, based on training data including the input samples, the first machine learning model. A second machine learning model may be determined to be a duplicate of the first machine learning model based on a comparison of the first digital watermark embedded in the first machine learning model and a second digital watermark extracted from the second machine learning model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.