Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hidden model training and use method, device and computer readable storage medium

A model training and model technology, applied in the field of communication, can solve problems such as poor hiding effect

Active Publication Date: 2022-05-27
SHENZHEN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a hidden model training and use method, device and computer-readable storage medium, aiming to solve the technical problem of poor hiding effect of existing steganography technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hidden model training and use method, device and computer readable storage medium
  • Hidden model training and use method, device and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0036] The development trend of contemporary steganography is mainly reflected in several branches: digital media information hiding, language steganography, file system steganography, and network steganography. The history of digital media steganography can be traced back to the 1970s, and its development methods include patchwork, significant bit modification, texture block encoding, etc. These techniques are used in lossy or lossless compressed images. Linguistic steganography is mainly accomplished by changing the paragraphs, word order or synonyms of the carrier text language. In today's development of steganography, a large amount of text information, even including spam, may become the carrier of text steganography. File system steganography refers to embedding steganographic information into an isolated computer environment, so that it can automatically search the encrypted files of the disk to achieve the purpose of obtaining information. Network steganography is th...

no. 2 example

[0053] This embodiment also provides a method for using a hidden model, where the hidden model is obtained by training the hidden model training method provided in the first embodiment, the hidden model at least includes a generator, and the method for using the hidden model includes:

[0054] The information to be hidden is input into the generator, and the generator outputs a hidden image based on the information to be hidden.

[0055] In some other examples of this embodiment, the information to be hidden here is a uniformly distributed hidden information sequence.

[0056] It should be understood that the information to be hidden can be converted into a hidden image to be hidden by the generator in the hidden model, so as to avoid the detection of the detector. The hidden model also includes a decoder and a discriminator, both of which are also trained by the hidden model training method provided in the first embodiment. It should be understood that the decoder correspond...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a hidden model training and using method, device and computer-readable storage medium. Since the hidden model training method is to train the generator model, the decoder model and the discriminator model, that is, the generator performs self- The data used for correction is not limited to data samples, but also includes the reverse transmission data of the decoder and the discriminator. Therefore, the steganography technology based on this training method will have a better hiding effect; at the same time, different from the traditional, The method of embedding the information to be hidden into a real picture, the present invention directly uses the information to be hidden to generate an image, the existing information detector will not be easy to identify the image with the information to be hidden and further extract the information in the image, in summary, this The method provided by the invention has better hiding effect.

Description

technical field [0001] The present invention relates to the field of communication technologies, and more particularly, to a hidden model training and use method, device and computer-readable storage medium. Background technique [0002] In the field of information hiding, the traditional steganography method realizes information steganography by embedding the information to be hidden in the real picture, but the information detector will easily identify the picture with hidden information and extract the hidden information from it, That is, the existing steganography technology is inconvenient to hide information because it is easy to be detected and extracted, and it has a poor hiding effect. Therefore, it is urgent to provide a method to improve the hiding effect of information. SUMMARY OF THE INVENTION [0003] The main purpose of the present invention is to provide a hidden model training and use method, device and computer-readable storage medium, aiming at solving t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T1/00
CPCG06T1/0021G06T2207/20081
Inventor 谭舜泉李振军莫显博欧培
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com