Key generation method based on deep learning generative adversarial network

Abstract

The invention provides a secret key generation method based on a deep learning generative adversarial network, and the method comprises the steps: firstly preparing a training set image; constructinga key generation network: constructing the key generation network according to a generator network and a discriminator network, and inputting the training set image into the key generation network; and training a key generation network: training the key generation network by using a deep learning method to generate a key. The secret key generated by the method has the characteristics of large secret key space, pseudo randomness, one-time pad and sensitivity to an initial value. The method is one of the earliest researches of trying to adopt a deep learning method in the field of key generation, and the generated key is used for encrypting the plaintext medical image, so that relatively high security can be brought.

Description

technical field [0001] The invention belongs to the technical field of communication, and in particular relates to a key generation method based on deep learning to generate an adversarial network. Background technique [0002] According to the different ways of encrypting plaintext, cryptosystems can be divided into block ciphers and stream ciphers. Traditional block key encryption methods such as Data Encryption Standard (DES), International Data Encryption Algorithm (IDEA) and Advanced Encryption Standard (AES) have been widely used in image encryption. Compared with block ciphers, stream ciphers have the advantages of high security, fast encryption and decryption speed, small error expansion, good synchronization, and low implementation cost. For stream ciphers, the core issue is the design of stream cipher generators. The strength of stream ciphers depends entirely on the randomness and unpredictability of the sequences generated by the stream cipher generators. At pr...

AI Technical Summary

Problems solved by technology

In order to obtain good encryption performance, the manual design process is difficult and time-consuming work, which requires not only professional information security knowledge, but also prior knowledge of mathematical theory

Images