Image Encryption Algorithm based on Convolutional Neural Network and Four Square Matrix Encoding
Bin Ge, Ting Wang, Chenxing Xia, Gaole Dai · 2022
To balance the performance of chaos and the algorithm’s efficiency, a Henon-Modulated-Iterative (HMI) map is constructed in this paper. And the chaotic characteristics of the HMI map are analyzed from three aspects: bifurcation map, Lyapunov exponent and balance degree. On this basis, an image encryption algorithm based on a convolutional neural network (CNN) and four square matrix encoding is proposed. Then, the random sequence generation module is designed using CNN, and the generated random sequence is used to construct the scrambling coordinate matrix and modify the position of the pixel values. Finally, the scrambled image is diffused by four square matrix encoding so that the pixel values are evenly distributed, while non-sequential diffusion using hexadecimal addition and subtraction rules improves the security of the encryption algorithm. Experimental results show that the encryption algorithm proposed in this paper has a good encryption effect and can resist various attacks.