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

A Secure Embedding-Free Steganography Method Based on Generative Adversarial Networks

A safe and steganographic technology, applied in the field of information security, can solve problems such as dissatisfaction, low recovery accuracy, and difficulty in resisting security threats, and achieve the effect of ensuring security.

Active Publication Date: 2022-03-15
HEFEI UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing embedding-free steganography algorithms, especially those based on GAN, have some problems, including small embedding capacity, low recovery accuracy, and difficulty in resisting known generation model attacks, known extraction model attacks and training Common security threats such as extraction model attacks do not satisfy the Kerckhoffs criterion in modern cryptography

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
  • A Secure Embedding-Free Steganography Method Based on Generative Adversarial Networks
  • A Secure Embedding-Free Steganography Method Based on Generative Adversarial Networks
  • A Secure Embedding-Free Steganography Method Based on Generative Adversarial Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In this example, see figure 1 , a secure embedding-free steganography method based on generative adversarial networks, is applied in a network environment composed of a sender, a receiver, a discriminator and a third party, and proceeds as follows:

[0058] Step 1. Use the openssl tool to generate a key pair, including: generate the key en_key and extract the key de_key;

[0059] Step 2. The third party distributes the generated key en_key to the sender, and distributes the extracted key de_key to the receiver;

[0060] Step 3. Train a GAN-based secure embedding-free steganographic model:

[0061] Step 3.1, obtain a real image set and use it as a pre-training data set w;

[0062] In a specific embodiment, the image data set FFHQ is used as the pre-training data set. The dataset contains 70,000 128×128×3 high-definition face images, and these photos have strong diversity, including age, accessories (glasses, hats), etc.

[0063] Step 3.2, let the safe embedding-free ...

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 secure non-embedded steganographic method based on a generative confrontation network, the steps of which include: 1 training a steganographic model based on a generative confrontation network, 2 encrypting secret information, and 3 encrypting and extracting secret information. The invention can solve common security threats such as known generation model attack, known extraction model attack, training extraction model attack, etc., so as to meet the security requirements of information steganography and extraction in the process of communication transmission.

Description

technical field [0001] The invention belongs to the technical field of information security, in particular to a secure non-embedding steganography method based on generative adversarial networks. Background technique [0002] Information hiding is a technology used for secret communication. Through information hiding algorithm, secret information can be transmitted without being noticed by a third party. Steganography is an important way to hide information. It mainly achieves the goal by embedding and modifying the carrier medium, while keeping the distortion of the carrier quality due to the modification within a certain range, and will not arouse the vigilance of the third party. Early spatial digital image steganography algorithms mainly used the insensitivity of human vision to small changes in the image, and replaced the least significant bit of image pixels with secret information. The security of adaptive steganography is challenged by powerful deep learning-based s...

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): H04L9/40H04L9/08G06T1/00G06N3/04G06N3/08
CPCH04L63/0442H04L9/0825H04L9/0861G06T1/0021G06N3/08G06T2201/005G06N3/045
Inventor 胡东辉张雨蒋文杰严淞
Owner HEFEI UNIV OF TECH
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