Membership leakage quantification to verify data removal
US12093793B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 3, 2021 |
| Grant date | Sep 17, 2024 |
| Priority date | — |
| Expiry date | Jul 20, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method, computer system, and a computer program product for testing a data removal from a trained machine learning model trained with a training data set are provided. A new machine learning model is trained by using an altered data set that includes training data from the training data set. The altered data set is without removal data. A first forgetting mechanism is applied to the trained machine learning model to form a first revised machine learning model. The applying includes removing the removal data from the trained machine learning model. A first membership leakage quantification on the first revised machine learning model is performed to quantify a first membership leakage of the removal data and that uses the new machine learning model for comparison. A first leakage score is determined from the first membership leakage quantification to test the forgetting mechanism.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.