Physical layer secrecy method and system based on mutual information estimation neural network
A technology of mutual information and neural network, which is applied in the field of physical layer security, physical layer security method and system based on mutual information estimation neural network, can solve the problems that are difficult to completely remove, the bit error rate of the receiving end increases, and the synchronization error occurs and other issues to achieve the effect of increasing noise
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0072] According to a kind of physical layer security method based on mutual information estimation neural network provided by the present invention, comprising:
[0073] Step S1: Based on mutual information estimation and end-to-end deep learning, train the encoder and decoder respectively to obtain a trained encoder and a trained decoder;
[0074] Step S2: Use the trained encoder and trained decoder to perform physical layer secure transmission.
[0075] Specifically, the step S1 adopts:
[0076] Step S1.1: Construct encoder, decoder and mutual information estimator;
[0077] Step S1.2: Train the decoder through end-to-end deep learning, and obtain the trained decoder;
[0078] Step S1.3: Train the mutual information estimator by sending the original bits and the channel output, and obtain the trained mutual information estimator;
[0079] Step S1.4: Obtain the end-to-end bit error rate through the trained decoder, and obtain the mutual information of the eavesdropper thr...
Embodiment 2
[0147] Embodiment 2 is a preferred example of embodiment 1
[0148] The present invention provides a physical layer security method based on mutual information estimation and end-to-end deep learning, such as figure 1 As shown, it includes the following steps: Step S1: Train the encoder and decoder based on mutual information estimation and end-to-end deep learning. Step S1 comprises the following steps:
[0149] Neural network construction steps: construct encoder, decoder and mutual information estimator. Construct encoder neural network, decoder neural network and mutual information estimator neural network.
[0150] The neural network is a fully connected neural network, including an input layer, a hidden layer and an output layer. The input data of the encoder includes the original bit and the pseudo-random number sequence, and the output data of the encoder is the processed signal. The input data of the decoder includes the signal output by the channel and the pseudo...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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