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

Secure steganography method and device based on generative adversarial networks

A network and security technology, applied in the information field, can solve the problems of insecure steganography method, poor network discrimination effect, and insignificant network effect of steganalysis, so as to achieve good steganalysis effect, fast training speed, and training time. reduced effect

Active Publication Date: 2018-01-09
INST OF INFORMATION ENG CAS
View PDF2 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004]The method proposed in Denis and Burnaev (ICLR 2016Open Review, 2016) has some limitations, and experiments show that its steganographic method is not secure enough
The network in this paper is suitable for embedding the same key, when using random keys, the network is not good at discriminative
In addition, the effect of its steganalysis network is not obvious

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
  • Secure steganography method and device based on generative adversarial networks
  • Secure steganography method and device based on generative adversarial networks
  • Secure steganography method and device based on generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0044] Example 1 Secure Steganography Method Based on Generative Adversarial Networks

[0045] Take the CelebA face dataset as an example:

[0046] 1) Under the framework of WGAN (Wasserstein Generative Adversarial Networks, Wasserstein Generative Adversarial Networks), the noise signal z is input to the generation network G, and the carrier image I is generated by the generation network G;

[0047] 2) The discrimination network D and the generation network G compete with each other, so that the carrier image I generated by G is closer to the real image;

[0048] 3) The discriminant network D performs discriminant analysis on the carrier image I generated by G, and obtains the probability of judging it as a real picture or a fake picture;

[0049] 4) Embed the generated carrier image I into information off-line, first use the LSB fixed key to embed to obtain the steganographic image I', input I and I' to the steganalysis network S at the same time, and judge whether it is the...

example 2

[0056] Example 2 Secure Steganography Method Based on Generative Adversarial Networks

[0057] Taking the CelebA face dataset as an example, in this experiment, by setting different seed values, we compare the deceptiveness of the generated images to the steganalysis network after information embedding under different parameters. The seed value refers to controlling the repeatability of the experiment under the condition of a certain random number, which is reflected in the present invention as controlling the randomness of the generated image.

[0058] 1) Under the WGAN framework, the noise signal z is input to the generation network G, and the carrier image I is generated by the generation network G;

[0059] 2) The discrimination network D and the generation network G compete with each other to generate a carrier image I that is closer to the real image;

[0060] 3) The discriminant network D performs discriminant analysis on the generated carrier image I, and obtains the ...

example 3

[0069] Example 3 Secure Steganographic Device Based on Generative Adversarial Networks

[0070] The secure steganography device based on the generative confrontation network includes: a generation network unit, used to generate a carrier image to embed information under the framework of the generative confrontation network; a discriminant network unit, used to judge the authenticity of the generated carrier image , and through the dynamic game process with the generating network unit, the carrier image generated by the generating network unit is close to the real image; the steganographic unit is used to embed information on the carrier image generated by the generating network unit. Further, the device also includes a steganalysis network unit, which is used to perform binary classification on the input carrier image and the steganographic image, and obtain the accuracy rate of classification into the original image and the steganographic image.

[0071] The present invention...

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 relates to a secure steganography method and device based on generative adversarial networks. The method includes: generating a carrier image, into which information needs to be embedded, through the generator network under a generative adversarial network framework, and judging authenticity of the generated carrier image through the discriminator network, enabling the carrier image,which is generated by the generator network, to be close to a real image through a dynamic game process of the generator network and the discriminator network; carrying out embedding of the information on the carrier image generated by the generator network; and then utilizing a steganalysis network to carry out binary classification on the input carrier image and a steganographed image to obtainaccuracy rates of classification into an original image and the steganographic image. According to the method, the generated carrier image is closer to the real image visually, a generation speed isfaster, and steganographic security can be improved.

Description

technical field [0001] The invention belongs to the field of information technology and relates to information steganography technology, in particular to a secure steganography method and device based on a generative confrontation network. Background technique [0002] Information steganography is one of the main branches of information hiding. Information hiding is to use the sensory redundancy of human sensory organs to digital signals to hide a set of secret information (authorization serial number, message or copyright information, etc.) into the carrier information, without affecting the sensory effect and use value of the host signal. This makes it difficult for possible attackers to judge whether the secret information exists, and it is even more difficult to intercept it, thereby ensuring the security of information transmission. With the development of science and technology, information hiding technology has become a new research focus, especially the wide applica...

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
IPC IPC(8): G06F21/10G06F21/60G06T1/00
Inventor 张晓宇石海超
Owner INST OF INFORMATION ENG CAS
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