General Image Fast Encryption Algorithm for Deep Learning Compression and Reconstruction

Abstract

Aiming at the problems of long time-consuming in image compression encryption and color distortion of the decrypted image, a fast and safe general image encryption algorithm is proposed. The compression network uses bilinear interpolation and a fully connected layer for compression preprocessing to prevent the loss of color information. Convolution layer improves compression rate and reduces time complexity in this algorithm. In the encryption part, the chaotic sequence dynamically selects the pixel block and the pixel points in the block combining the XOR operation to perform pixel diffusion, which can improve the randomness of the algorithm. In the improved bilinear convolution neural network, bilinear and convolutional layers are used to obtain the image contour features. And the fully connected layer obtains color information for image reconstruction. This algorithm realizes the integration of compression, encryption, decryption and restoration of grayscale and RGB format color images. The experimental results show that the various encryption indexes of this algorithm are close to ideal values. It has good encryption security and anti-attack ability. Moreover, the encryption time is greatly shortened. On the 500 test set (BSD500) commonly used in image processing, when the sampling rate is 0.25, 0.10, 0.04 and 0.01, the peak signal-to-noise ratio can reach to 29.01 dB, 25.69 dB, 23.75 dB and 21.45 dB, which is better than FCLBCNN. This encryption algorithm effectively solves the color distortion problem of reconstructed images and has better encryption effects and wider applicability.