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:
Oct. 27, 2026

Filed:

Mar. 30, 2021
Applicant:

Amazon Technologies, Inc., Seattle, WA (US);

Inventors:

Sergul Aydore, Brooklyn, NY (US);

Jeffrey Earl Bickford, Thornton, CO (US);

Ecenaz Erdemir, London, GB;

Luca Melis, New York City, NY (US);

Mohamadali Torkamani, Scarsdale, NY (US);

Assignee:

Amazon Technologies, Inc., Seattle, WA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2023.01); G06F 17/16 (2006.01); G06N 3/04 (2023.01);
U.S. Cl.
CPC ...
G06N 3/08 (2013.01); G06F 17/16 (2013.01); G06N 3/04 (2013.01);
Abstract

Disclosed are systems and methods for training deep neural networks ('DNNs') to increase the detection robustness of those DNNs to adversarial attacks through the use of non-uniform perturbations of training data that consider feature characteristics of features of the training data that are used to train the DNN. Features of training data are perturbed in a non-uniform manner based at least in part on the correlations of the different features and/or the importance of those features in detection of malicious data by the DNN.


Find Patent Forward Citations

Quick Actions:

Aydore, Sergul. (2026). Adversarial training of deep neural networks using non-uniform perturbations (U.S. Patent No. 12775836). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12775836

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…