Machine learning model fingerprinting
US11921903B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 1, 2023 |
| Grant date | Mar 5, 2024 |
| Priority date | — |
| Expiry date | Jun 1, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F21/629
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Data is received that characterizes artefacts associated with each of a plurality of layers of a first machine learning model. Fingerprints are then generated for each of the artefacts in the layers of the first machine learning model. These generated fingerprints collectively form a model indicator for the first machine learning model. It is then determined whether the first machine learning model is derived from another machine learning model by performing a similarity analysis between the model indicator for the first machine learning model and model indicators generated for each of a plurality of reference machine learning models each comprising a respective set of fingerprints. Data characterizing the determination can be provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.