Multi-Image Encryption Based on Compressed Sensing and Deep Learning in Optical Gyrator Domain

Abstract

In this paper, a multi-image encryption scheme based on compressed sensing (CS) and deep learning in the optical gyrator domain is proposed. Firstly, multiple plaintext images are compressed by CS to obtain multiple measurements, and then the pixels of each measurement are scrambled by using a chaotic system. Secondly, the scrambled measurements are combined into a matrix and diffused by XOR operation with a chaotic matrix. Finally, the diffused matrix is encoded with a random phase and an optical gyrator transform to obtain a complex-valued matrix, and the amplitude of the complex-valued matrix is taken as the ciphertext. In decrypt, plaintext images are reconstructed from the CS measurements by a neural network, which achieves high reconstruction speed and quality compared with the traditional algorithm. Especially, the data amount of plaintext images can be compressed by up to 8 times while achieving high decryption quality. To our best knowledge, CS reconstruction algorithms based on deep learning is firstly used for image encryption. Moreover, the proposed scheme is highly robust against occlusion, noise, and chosenplaintext attack.

Chaotic Image Encryption: State-of-the-Art, Ecosystem, and Future Roadmap

“…A differ-ent proposal by Joshi et al [240] also uses neural networks for encryption, but additionally adds impurities to confuse analysts. Other utilized techniques include multi-layer [241] and multi-image [242].…”

Explore the potential of deep learning and hyperchaotic map in the meaningful visual image encryption scheme

“…Therefore, there are some limitations on the time cost of their image reconstruction. For this reason, [27, 28] proposed deep learning‐based CS in image encryption schemes instead of traditional CS methods, which can effectively improve the reconstruction speed and the quality of reconstructed images. However, it should be noted that the above works will produce noise‐like secret images, which easily attract the attention of attackers.…”

“…Comparison with others. ] encrypted a meaningful plain image of size M × N to obtain a noise-like image of M × N size [20,21,27,28]. introduced a compressed sensing algorithm to compress and encrypt a meaningful plain image of size M × N to obtain a noise-like secret image with a size of (M/2) × (N/2) or (M/4) × N. Noise-like secret images are easy to attract the attention of attackers and are intercepted during transmission.Our image encryption scheme uses deep learning, hyperchaotic map and matrix coding to compress and encrypt a meaningful plain image of size M × N, and then embed it into a meaningful carrier image of size M × N to obtain a cipher image.…”

Single Exposure Phase-Only Optical Image Encryption and Hiding Method via Deep Learning

“…Meanwhile, in 3D image hiding and 3D cryptosystem, deep revolutionary neural networks are used to resolve the problem of low resolution effectively [24,25]. Various DLbased methods have been implemented to enhance image security and cryptanalysis, which are not limited to single image, but also include multiple images [26,27]. The use of POIEH technology can afford high security and flexibility.…”