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

Spatial-domain image steganography method and system based on generative adversarial network

A network and image technology, applied in the field of information steganography, can solve the problem of no solution in the field of image steganography in airspace, and achieve the effect of improving security and adaptability, low requirements, and a small number of network structure parameters

Active Publication Date: 2018-07-31
SUN YAT SEN UNIV
View PDF7 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since image steganography and steganalysis are two aspects of mutual game and mutual confrontation, the generative adversarial network in deep learning provides new ideas for image steganography and steganalysis, but considering the security and self-sufficiency of steganography Adaptability, the field of spatial image steganography still does not have a good solution

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
  • Spatial-domain image steganography method and system based on generative adversarial network
  • Spatial-domain image steganography method and system based on generative adversarial network
  • Spatial-domain image steganography method and system based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A spatial image steganography method based on generative adversarial networks, such as figure 1 shown, including the following steps:

[0036] S1: Input the carrier image into the generating network, and obtain a probability map with the same size as the carrier image after being processed by the generating network. In the field of spatial image steganography, the traditional method is to realize the adaptiveness of information embedding by minimizing the additive distortion function, and the present invention uses the embedding probability to replace the distortion

[0037] p i,j =ln(1 / ρ i,j -2), where p represents the embedding probability. Unlike distortion, the higher the embedding probability, the greater the possibility of embedding. The present invention proposes to use a U-shaped network as a generating network, and input the original image x to the attached figure 2 The U-shaped generative network shown, obtains the probability map: p=Ugen(x).

[0038] Th...

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 spatial-domain image steganography method and system based on generative adversarial network. The carrier image is converted into a probability graph through the generation network of a U-shaped structure, and then the probability graph is coded by utilizing a hyperbolic tangent coding module, a tampering point graph is generated, and the carrier image and the tampering point graph are added to generate a secret-carrying image; and then a steganography analysis network is used for distinguishing the carrier image and the secret-carrying image, and the classification result is fed back to the generation network in an error mode; and finally, the trained generation network and the coding module are combined together, as a final spatial-domain image steganography model, the carrier image is input into the whole model, and the secret-carrying image is output. The invention further discloses a space-domain image steganography system based on the generative adversarial network, and the system includes a generation network module, an encoding module and an image steganography module. According to the spatial-domain image steganography method based on the generative adversarial network, the security is obviously improved, and the design is simple.

Description

technical field [0001] The present invention relates to the field of information steganography, and more specifically, to a method and system for spatial image steganography based on generative adversarial networks. Background technique [0002] In the covert communication technology, there are two commonly used methods, one is cryptography, the sender encrypts the secret information through encryption technology, and the information is transmitted in the form of ciphertext, and the receiver uses the decryption algorithm and key to transmit the information after receiving the information. Interpreting ciphertext into plaintext, the attack on cryptography is called deciphering; the other is steganography, where the sender hides the secret information in the carrier and spreads it through open channels. After the receiver receives the carrier containing the secret information , to extract the secret information from the carrier. The opposite of steganography is steganalysis, w...

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 Applications(China)
IPC IPC(8): G06T1/00
CPCG06T1/0028G06T2207/20084
Inventor 康显桂刘凯阳建华
Owner SUN YAT SEN 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