Fuzzy key communication system and confrontation network system based on deep learning

Abstract

The present invention discloses a fuzzy key communication system and confrontation network system based on in-depth learning. The system comprises a communication party Alice and a communication partyBob; the communication party Alice includes an encryption model; the encryption model is obtained after in-depth learning by a first neural network model; the communication party Bob includes a decryption model, and the decryption model is obtained after in-depth learning by a second neural network model, for inputting a key and a ciphertext, and decrypting the input ciphertext according to the fuzzy key to obtain plaintext information; the second neural network model includes a second fully connected layer, a third fully connected layer, and multi-layer convolutional layer from input to output; the key entered by the decryption model of the communicating party Bob is a fuzzy key. The present invention also discloses a confrontation network that is obtained by in-depth learning after thecommunication system joins an Eve model. The system can enhance communication performance of network in a fuzzy key communication environment, and realize accurate communication under the fuzzy key environment.

Description

technical field [0001] The invention belongs to the field of computer technology and information security communication technology, and in particular relates to a deep learning-based fuzzy key communication system and an adversarial network system. Background technique [0002] With the development of deep learning technology, it has also begun to try to use it in various fields. General encryption algorithms are designed by people themselves, but now it is possible to make encryption algorithms using generative adversarial networks in deep learning. Among them, the confrontation network Google Brain is confronted by two neural networks. One neural network Eve is responsible for deciphering the ciphertext of the communication, and the other neural network is composed of two parts Alice and Bob; the encrypted communication between Alice and Bob, Eve is responsible for deciphering the communication Content; the above two neural networks carry out the network confrontation bet...

AI Technical Summary

Problems solved by technology

[0003] At present, the information protection encryption algorithm can be learned through Google Brain's confrontation network. This model can also realize encrypted communication when there is a small loss or difference in the key obtained by Bob. However, when there is a certain amount of information loss in the communication process, Bob will There is no guarantee that plaintext can be restored

Images