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:
Nov. 24, 2020

Filed:

Feb. 11, 2020
Applicant:

Calypso Ai Corp, San Mateo, CA (US);

Inventors:

Neil Serebryany, San Francisco, CA (US);

Brendan Quinlivan, San Francisco, CA (US);

Victor Ardulov, Los Angeles, CA (US);

Ilja Moisejevs, Dublin, IE;

David Richard Gibian, New York, NY (US);

Assignee:

CALYPSO AI CORP, San Mateo, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 21/56 (2013.01); G06N 20/00 (2019.01); G06N 7/00 (2006.01);
U.S. Cl.
CPC ...
G06F 21/566 (2013.01); G06N 7/005 (2013.01); G06N 20/00 (2019.01); G06F 2221/033 (2013.01);
Abstract

Robustness of a machine learning model can be characterized by receiving a file with a known, first classification by the machine learning model. Thereafter, a selection is made as to which of a plurality of perturbation algorithms to use to modify the file. The perturbation algorithm is selected as to provide a shortest sequence of actions to cause the machine learning model to provide a desired classification. Subsequently, the received file is iteratively modified using the selected perturbation algorithm and inputting the corresponding modified file into the machine learning model until the machine learning model outputs a known, second classification. Related apparatus, systems, techniques and articles are also described.


Find Patent Forward Citations

Loading…