Patent · US Active

Adding adversarial robustness to trained machine learning models

US11334671B2 · kind B2 · utility

1Cited by

4References

17Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Beat Buesser · Dublin, IE
Maria Irina Nicolae · Dublin, IE
Ambrish Rawat · Dublin, IE
Mathieu Sinn · Dublin, IE
Ngoc Minh Tran · Dublin, IE
Martin Wistuba · Dublin, IE

Key dates

Filing date	Oct 14, 2019
Grant date	May 17, 2022
Priority date	—
Expiry date	Oct 14, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06N20/00
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

One or more hardened machine learning models are secured against adversarial attacks by adding adversarial protection to one or more previously trained machine learning models. To generate the hardened machine learning models, the previously trained machine learning models are retrained and extended using preprocessing layers or using additional network layers which test model performance on benign or adversarial samples. A rollback strategy is additionally implemented to retain intermediate model states during the retraining to provide recovery if a training collapse is detected.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.