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:
May. 24, 2022

Filed:

Jul. 24, 2019
Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Heiko H. Ludwig, San Francisco, CA (US);

Hogun Park, West Lafayette, IN (US);

Mu Qiao, Belmont, CA (US);

Peifeng Yin, San Jose, CA (US);

Shubhi Asthana, Santa Clara, CA (US);

Shun Jiang, San Jose, CA (US);

Sunhwan Lee, San Mateo, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
H04N 21/81 (2011.01); G06Q 30/02 (2012.01); G06N 5/04 (2006.01); G06F 17/27 (2006.01); G06N 3/04 (2006.01); G06F 16/901 (2019.01); G06K 9/62 (2022.01);
U.S. Cl.
CPC ...
G06N 3/04 (2013.01); G06F 16/9024 (2019.01); G06K 9/6267 (2013.01); G06N 5/045 (2013.01);
Abstract

Embodiments relate to systematic explanation of neural model behavior and effective deduction of its vulnerabilities. Input data is received for the neural model and applied to the model to generate output data. Accuracy of the output data is evaluated with respect to the neural model, and one or more neural model vulnerabilities are identified that correspond to the output data accuracy. An explanation of the output data and the identified one or more vulnerabilities is generated, wherein the explanation serves as an indicator of alignment of the input data with the output data.


Find Patent Forward Citations

Loading…