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:
Jan. 10, 2023

Filed:

Apr. 21, 2020
Applicant:

Hrl Laboratories, Llc, Malibu, CA (US);

Inventors:

Soheil Kolouri, Agoura Hills, CA (US);

Heiko Hoffmann, Simi Valley, CA (US);

Assignee:

HRL LABORATORIES, LLC, Malibu, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 21/56 (2013.01); G06F 8/41 (2018.01); G06K 9/62 (2022.01); G06N 3/04 (2006.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06F 21/566 (2013.01); G06F 8/41 (2013.01); G06K 9/6267 (2013.01); G06N 3/04 (2013.01); G06V 10/82 (2022.01);
Abstract

Described is a system for detecting backdoor attacks in deep convolutional neural networks (CNNs). The system compiles specifications of a pretrained CNN into an executable model, resulting in a compiled model. A set of Universal Litmus Patterns (ULPs) are fed through the compiled model, resulting in a set of model outputs. The set of model outputs are classified and used to determine presence of a backdoor attack in the pretrained CNN. The system performs a response based on the presence of the backdoor attack.


Find Patent Forward Citations

Quick Actions:

Kolouri, Soheil. (2023). System and method for detecting backdoor attacks in convolutional neural networks (U.S. Patent No. 11550914). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/11550914

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

Loading…