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

Image encryption algorithm based on discrete Hopfield neural network

A neural network and encryption algorithm technology, applied in the field of image encryption algorithm, can solve problems such as plaintext attacks

Active Publication Date: 2021-09-07
贵州宇鹏科技有限责任公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this scheme, since the plaintext image and the key are independent of each other, the key stream used for encryption of different plaintext images is uniquely determined. Therefore, this type of encryption scheme is vulnerable to chosen plaintext attacks

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
  • Image encryption algorithm based on discrete Hopfield neural network
  • Image encryption algorithm based on discrete Hopfield neural network
  • Image encryption algorithm based on discrete Hopfield neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] 1 Discrete HOPField Neural Network

[0080] The Hopfield Neural Network was earliered by American physicist Hopfield in 1982 [17]. It is mainly used to simulate the memory mechanism of biological neural networks. The Hopfield neural network is a fully connected neural network. . The specific form of the third-order neural network is as follows:

[0081]

[0082] In order to confirm its pseudo-randomability, NIST randomness testing for the Hopfield neural network [18], when the P value is greater than 0.01, it is considered to pass the test. The results are shown in Table 1. The random test results show that the Hopfield chaotic neural network based on the weight matrix has pseudo-randomability.

[0083] Table 1. Nist randomity test

[0084]

[0085]

[0086] 2 proposed encryption algorithm

[0087] The image encryption algorithm we propose includes the simultaneous and diffusion algorithm associated with color images R, G, and B three-channel association, and the seco...

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 an image encryption algorithm based on a discrete Hopfield neural network, and the algorithm comprises the following steps: S1, generating a key stream based on a third-order neural network of the Hopfield neural network, and carrying out the simultaneous scrambling diffusion operation of an R channel, a G channel and a B channel of a color image through the key stream, and obtaining an R_3 channel matrix, a G_3 channel matrix and a B_3 channel matrix after scrambling diffusion; S2, performing secondary diffusion operation on the three channel matrixes R_3, G_3 and B_3 after scrambling diffusion to obtain an output ciphertext image. According to the image encryption algorithm, the influence of scrambling and diffusion separated attacks on the encryption algorithm can be effectively avoided, the encryption performance is good, and various attacks can be resisted.

Description

Technical field [0001] The present invention relates to an image encryption algorithm based on discrete HOPField neural network, belonging to the field of image encryption. Background technique [0002] With the rapid development of network media, more and more image data is transmitted through public networks, ensuring that information transmission is critical. A encryption method that guarantees image integrity is to transfer the plaintext image to a noise image re-transmitted, and this information hidden manner improves the security of the transmission. Currently, more and more image encryption algorithms are proposed. Due to the particularity of the image, for example, the data capacity, high correlation between the pixels, the conventional data encryption algorithm, such as DES, AES, and IDEA, etc., such as DES, AES, and IDEA, etc., in recent years, various types of encryption The algorithm is proposed in a large number, for example, chaotic image encryption, based on compre...

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): G06F21/60G06N3/04G06N3/08H04L9/08H04L29/06
CPCG06F21/602G06N3/08H04L9/0816H04L63/0435G06N3/044
Inventor 王高峰徐子同张赛高涛
Owner 贵州宇鹏科技有限责任公司
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