Protecting a machine learning model
US11036857B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 15, 2018 |
| Grant date | Jun 15, 2021 |
| Priority date | — |
| Expiry date | Aug 30, 2039 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L63/1441
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial example; training a defender to protect the model from the first adversarial example by updating a strategy of the defender based on predictive results from classifying the first adversarial example; updating the attack tactic based on the predictive results from classifying the first adversarial example; generating a second adversarial example by modifying the original input using the updated attack tactic, wherein the trained defender does not protect the model from the second adversarial example; and training the defender to protect the model from the second adversarial example by updating the at least one strategy of the defender based on results obtained from classifying the second adversarial example.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.