The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 06, 2023

Filed:

Nov. 12, 2020
Applicant:

Wells Fargo Bank, N.a., San Francsico, CA (US);

Inventors:

Tarun Joshi, San Francisco, CA (US);

Rahul Singh, San Francisco, CA (US);

Vijayan Nair, San Francisco, CA (US);

Agus Sudjianto, San Francisco, CA (US);

Assignee:

Wells Fargo Bank, N.A., San Francisco, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 40/284 (2020.01); G06F 40/253 (2020.01); G06N 20/00 (2019.01); G06F 21/57 (2013.01); G06F 40/30 (2020.01);
U.S. Cl.
CPC ...
G06F 40/284 (2020.01); G06F 21/577 (2013.01); G06F 40/253 (2020.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01); G06F 2221/033 (2013.01);
Abstract

Systems, apparatuses, methods, and computer program products are disclosed for determining robustness information for an NLP model. Modification rules, such as replacement rules and/or insertion rules, are used to generate instances of modified test data based on instances of test data that comprise words and have a syntax and a semantic meaning. The instances of test data and modified test data are provided to the NLP model and the output of the NLP model is analyzed to determine output changing instances of modified test data, which are instances of modified test data yielded output from the NLP model that is different and/or not similar to the output yielded from the NLP model for the corresponding instance of test data. Robustness information for the NLP model is determined based at least in part on the output changing instances of modified test data. White and/or black box attacks may be performed.


Find Patent Forward Citations

Loading…