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. 11, 2024

Filed:

Sep. 01, 2021
Applicant:

Nec Laboratories America, Inc., Princeton, NJ (US);

Inventors:

Zhengzhang Chen, Princeton Junction, NJ (US);

Haifeng Chen, West Windsor, NJ (US);

Liang Tong, Manchester, MO (US);

Assignee:

NEC Corporation, Tokyo, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2023.01); G06F 18/21 (2023.01); G06F 18/28 (2023.01); G06V 10/22 (2022.01); G06V 40/16 (2022.01);
U.S. Cl.
CPC ...
G06N 3/08 (2013.01); G06F 18/2163 (2023.01); G06F 18/28 (2023.01); G06V 10/22 (2022.01); G06V 40/171 (2022.01); G06V 40/172 (2022.01);
Abstract

Methods and systems for evaluating and enhancing a neural network model include constructing a surrogate model that corresponds to a target neural network model, based on a degree of knowledge about the target neural network model. Adversarial attacks against the surrogate model are generated, based on an attack goal, a level of attacker capability, and an attack model. The target neural network model is tested for accuracy under the generated adversarial attacks to determine a degree of robustness of the target neural network. Robustness of the target neural network model is enhanced by replacing facial occlusions in input images before applying the input images to the target neural network.


Find Patent Forward Citations

Loading…