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:
Apr. 30, 2024

Filed:

Mar. 21, 2019
Applicant:

The Regents of the University of California, Oakland, CA (US);

Inventors:

Bita Darvish Rouhani, San Diego, CA (US);

Huili Chen, San Diego, CA (US);

Farinaz Koushanfar, San Diego, CA (US);

Assignee:
Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/048 (2023.01); G06F 21/16 (2013.01); G06N 3/045 (2023.01); G06N 3/063 (2023.01); G06N 7/01 (2023.01); G06Q 20/12 (2012.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06Q 20/1235 (2013.01); G06F 21/16 (2013.01); G06N 3/045 (2023.01); G06N 3/048 (2023.01); G06N 3/063 (2013.01); G06N 7/01 (2023.01); G06V 10/82 (2022.01);
Abstract

A method may include embedding, in a hidden layer and/or an output layer of a first machine learning model, a first digital watermark. The first digital watermark may correspond to input samples altering the low probabilistic regions of an activation map associated with the hidden layer of the first machine learning model. Alternatively, the first digital watermark may correspond to input samples rarely encountered by the first machine learning model. The first digital watermark may be embedded in the first machine learning model by at least training, based on training data including the input samples, the first machine learning model. A second machine learning model may be determined to be a duplicate of the first machine learning model based on a comparison of the first digital watermark embedded in the first machine learning model and a second digital watermark extracted from the second machine learning model.


Find Patent Forward Citations

Loading…