Double-image encryption method based on convolutional neural network dynamic adaptive diffusion

Abstract

The invention discloses a double-image encryption method based on convolutional neural network dynamic adaptive diffusion, relates to the technical field of double-image encryption, and solves the problems of insufficient key space and insufficient randomness in an existing double-image encryption method and the security defect that known plaintext attacks and selected plaintext attacks cannot be effectively resisted. A random sequence generated by a 5D conservative chaotic system is subjected to a series of transformation to obtain L_Con as a convolution kernel of a convolutional neural network, and a plaintext-related coordinate pair is obtained. Two plaintext images are respectively divided into 8-bit binary forms, high 4 bits and low 4 bits are respectively combined, then the two images are scrambled by plaintext-related coordinate pairs, and finally, pixels of the images are further disturbed by using a dynamic adaptive diffusion method. The 5D conservative chaotic system has better pseudo-random characteristics, larger key space, higher sensitivity and higher capability of resisting various security attacks, so that the 5D conservative chaotic system has more stable chaotic characteristics, resistance to reconstruction attacks and the like.

Description

technical field [0001] The invention relates to the technical field of double-image encryption, in particular to a dynamic self-adaptive diffusion double-image encryption and decryption method based on a convolutional neural network and bitwise fused images. Background technique [0002] In recent years, the rapid development of information technology and telecommunication networks has led to an increase in the transmission of digital information from images to audio and video files. Therefore, researchers have conducted extensive studies to maintain the security of these data and protect it from unauthorized users. Encryption is one way to achieve high security. At the same time, due to its wide range of applications, including military, medical, etc., encryption technology has become one of the most widely used and active fields. Image data has its unique characteristics (large volume, high correlation between pixels, and high compressibility) that make it difficult and ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a convolutional neural network-based Dynamic Adaptive Diffusion Double Image Encryption and Decryption Method

Images