Method for protecting deep learning model based on confidential computing
US11886554B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Feb 28, 2023 |
| Grant date | Jan 30, 2024 |
| Priority date | — |
| Expiry date | Feb 28, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/0464
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention discloses a method for protecting a deep learning model based on confidential computing. In this solution, a use process of a deep learning model is divided into two stages: Data preprocessing and inference. At the data preprocessing stage, a data preprocessing model is mainly used to process inference data of an authorized user. The data preprocessing model is a lightweight processing module, which occupies less computing resources, and the data preprocessing model is deployed in a confidential computing environment. At the inference stage, an inference model is used to perform inference on preprocessed data, and the inference model is deployed in a common computing environment. In the entire process, copyright attestation of the deep learning model can be implemented without affecting inference accuracy of the model, and the infringement of the model copyright can be effectively resisted through model forgery, transfer learning, knowledge distillation, and the like.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.