Detecting and delaying effect of machine learning model attacks
US10824721B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 22, 2018 |
| Grant date | Nov 3, 2020 |
| Priority date | — |
| Expiry date | Jan 17, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N7/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
One embodiment provides a method for delaying malicious attacks on machine learning models that a trained using input captured from a plurality of users, including: deploying a model, said model designed to be used with an application, for responding to requests received from users, wherein the model comprises a machine learning model that has been previously trained using a data set; receiving input from one or more users; determining, using a malicious input detection technique, if the received input comprises malicious input; if the received input comprises malicious input, removing the malicious input from the input to be used to retrain the model; retraining the model using received input that is determined to not be malicious input; and providing, using the retrained model, a response to a received user query, the retrained model delaying the effect of malicious input on provided responses by removing malicious input from retraining input.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.