Research on the avalanche effect of image encryption based on the Cycle-GAN

Abstract

Aiming at the problem of the weak avalanche effect in the recently proposed deep learning image encryption algorithm, this paper analyzes the causes of weak avalanche effect in the neural network of Cycle-GAN step-by-step process and proposes an image encryption algorithm combining the traditional diffusion algorithm and deep learning neural network. In this paper, first, the neural network is used for image scrambling and slight diffusion, and then the traditional diffusion algorithm is used to further diffuse the pixels. The experiment in satellite images shows that our algorithm, with the help of the further diffusion mechanism, can compensate for the weak avalanche effect of Cycle-GAN-based image encryption and can change a pixel value to the original image, and the number of pixel change rate (NPCR) and unified average changing intensity (UACI) values can achieve 99.64% and 33.49%, respectively. In addition, our method can effectively encrypt the image where the encrypted image with high information entropy and low pixel correlation is obtained. The experiment on data loss and noise attack declares our method can identify the types and intensity of attacks. What is more, the key space is big enough, and the key sensitivity is high while the key has a certain randomness.

Survey on deep learning applications in digital image security

“…As we can see in Table 2, the end-to-end deep learning image algorithm in Ref. 54 has better values in correlation coefficients and NPCR than the other two traditional image encryption methods. Furthermore, in other indexes, the deep learning method also has a similar value to the other two methods.…”

Face Image Encryption Based on Feature with Optimization Using Secure Crypto General Adversarial Neural Network and Optical Chaotic Map

“…A user, a cloud, and a trusted third party make up this computer architecture, and the trusted third party is in charge of distributing random compressed sensing keys. In [ 19 ], a machine learning technique was used for an issue involving health, commercial, or other sorts of sensitive data, which necessitates not only precise estimates. Because the cloud does not have access to keys required to decrypt the data, encryption assures that it remains private.…”

A deep learning signed medical image based on cryptographic techniques

“…As shown in Table 6 which displays the comparative results assessing our proposed system with older systems due to their NPCR and UACI values, from the following analysis, it has been proved that the proposed scheme is robust and can withstand the differential assaults. [35] 0.9961 0.3357 Ding et al [23] 0.9959 0.2319 Bao and Xue [39] 0.9964 0.3349…”

“…Thus, the results confirm that our new suggested scheme can be able to effectively counteroffensive the information entropy. [35] 7.9944 Ding et al [23] 7.9986 Bao and Xue [39] 7.9972…”