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

A Low Bit Error Rate Adversarial Neural Network Encryption Training Method

A neural network and bit error rate technology, applied in the field of adversarial neural network encryption training with low bit error rate, can solve the problem of high bit error rate, and achieve the effect of simple and easy-to-understand methods

Active Publication Date: 2021-02-05
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned problems or deficiencies, in order to solve the problem of high bit error rate in existing adversarial neural network encryption training methods, the present invention provides a low bit error rate adversarial neural network encryption training method

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 Low Bit Error Rate Adversarial Neural Network Encryption Training Method
  • A Low Bit Error Rate Adversarial Neural Network Encryption Training Method
  • A Low Bit Error Rate Adversarial Neural Network Encryption Training Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0022] refer to figure 1 , the encryption network and the decryption network constitute the generator of the adversarial neural network, and the eavesdropping network constitutes the discriminator. First, the neural network structure of the encryption network and the decryption network is introduced. The first layer is a fully connected layer (FC), and the two N-bit input (encryption: plaintext and key, decryption: ciphertext and key) is used as the input of the first fully connected layer. After this 2N-bit vector passes through a 2N×2N fully connected layer, it passes through four consecutive The one-dimensional (1-d) convolutional layer, the convolutional layer is based on the number of input channels (in_channels), the number of ou...

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 the field of artificial intelligence, in particular to an adversarial neural network encryption training method with low bit error rate. The invention adjusts the polynomial loss function ratio by adding hyperparameter η to realize the adversarial neural network encryption training method with low bit error rate. In the encryption training process of the adversarial neural network, the hyperparameter η is added to adjust the proportion of each item of the generator polynomial loss function, and a training result with a low bit error rate is obtained through repeated training and testing. This method is simple. Understandable, easy to implement and works well.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an adversarial neural network encryption training method with low bit error rate. Background technique [0002] Adversarial neural networks are a deep learning model and one of the most promising approaches for unsupervised learning on complex distributions in recent years. The neural network trains a good generator through the mutual game learning of two modules, the generator and the discriminator. [0003] In 2016, Abadi and Andersen of the Google Brain team proposed the use of adversarial neural networks to learn encryption algorithms autonomously. The adversarial neural network consists of three neural networks, namely Alice, Bob, and Eve. Eve tries to eavesdrop on the communication content of Alice and Bob. , Alice and Bob try to learn how to protect their communication from Eve's eavesdropping. In continuous confrontation learning, Alice and Bob independently learn ...

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): G06N3/08G06F21/60
CPCG06F21/60G06N3/08
Inventor 刘洋刘一礼钱堃胡绍刚于奇
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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