Hiding Information and Images via Deep Learning

Patent №

US 11,080,809

Granted

2021-08-03

Filed 2019

Owner

GOOGLE INC.

AI components

3

ml · vision · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16614983

The present disclosure provides systems and methods for hiding information using deep neural networks. In one example, a computer-implemented method is provided to train neural networks for hiding images, which includes inputting a package image and a cover image into an image hiding neural network and generating a carrier image as an output, the carrier image comprising the package image hidden within the cover image. The method includes inputting the carrier image into an image decoding neural network and generating a reconstruction of the package image as an output. The method includes simultaneously training the image decoding neural network based at least in part on a first loss function that describes a difference between the package image and the reconstruction of the package image and the image hiding neural network based at least in part on the first loss function and on a second loss function that describes a difference between the cover image and the carrier image.

Machine learningVisionAI hardwareG06T 1/0021G06T 1/005G06N 3/045G06N 3/0455G06N 3/0464G06N 3/084G06N 3/09H04N 1/32144+3 more

AI classification

Vision1.00
Machine learning1.00
AI hardware1.00
Knowledge representation0.02
Natural language0.01
Planning0.01
Evolutionary computation0.01
Speech0.00

Ownership

GOOGLE INC.

assignment · 510530516

Assignors

BALUJA, SHUMEET, BALUJA, SHUMEET

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC