A robust compressed sensing image encryption algorithm based on GAN and CNN

Chai, Xiuli; Tian, Ye; Gan, Zhihua; Yang, Lu; Wu, Xiangjun; Long, Guoqiang

doi:10.1080/09500340.2021.2002450

Cited by 24 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These properties make the chaos-based image encryption algorithms can exhibit a good ability to protect image data. So far, the image encryption algorithms based on chaotic systems have been widely studied [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. In [ 8 ], an image encryption algorithm based on random integer cycle shift and logistic map is proposed.…”

Section: Introductionmentioning

confidence: 99%

“…In the proposed scheme, the chaotic sequence used in the encryption algorithm is constructed by the LSTM-ANN deep learning network. Chai et al [ 11 ] proposed a chaotic encryption algorithm based on generative adversarial network (GAN), convolutional neural network (CNN), and denoising network. In the proposed algorithm, the deep learning reconstruction scheme based on GAN improves the robustness of the encryption algorith, and the CNN denoiser improves the visual expression of the decrypted image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Domain Image Encryption Algorithm Based on Improved Henon Map

Chen

Xie

Zhang

2022

Entropy

View full text Add to dashboard Cite

A hybrid domain image encryption algorithm is developed by integrating with improved Henon map, integer wavelet transform (IWT), bit-plane decomposition, and deoxyribonucleic acid (DNA) sequence operations. First, we improve the classical two-dimensional Henon map. The improved Henon map is called 2D-ICHM, and its chaotic performance is analyzed. Compared with some existing chaotic maps, 2D-ICHM has larger parameter space, continuous chaotic range, and more complex dynamic behavior. Second, an image encryption structure based on diffusion–scrambling–diffusion and spatial domain–frequency domain–spatial domain is proposed, which we call the double sandwich structure. In the encryption process, the diffusion and scrambling operations are performed in the spatial and frequency domains, respectively. In addition, initial values and system parameters of the 2D-ICHM are obtained by the secure hash algorithm-512 (SHA-512) hash value of the plain image and the given parameters. Consequently, the proposed algorithm is highly sensitive to plain images. Finally, simulation experiments and security analysis show that the proposed algorithm has a high level of security and strong robustness to various cryptanalytic attacks.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Hybrid Domain Image Encryption Algorithm Based on Improved Henon Map

Chen

Xie

Zhang

2022

Entropy

View full text Add to dashboard Cite

show abstract

“…DL, which uses multilayer neural networks (NNs) to extract features from raw input photos, has also attracted much interest in solving the problem. The advantages of convolution neural networks (CNNs) [ 8 ] are established in computer vision applications and picture domain transfer [ 9 ]. Image transfer from one domain to another is thought of as a texture transfer issue, to learn mapping connection amid an input image and output image from a set of matched image pairs.…”

Section: Related Workmentioning

confidence: 99%

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

Alsafyani

Alhomayani

Alsuwat

et al. 2023

Sensors

View full text Add to dashboard Cite

Demand for data security is increasing as information technology advances. Encryption technology based on biometrics has advanced significantly to meet more convenient and secure needs. Because of the stability of face traits and the difficulty of counterfeiting, the iris method has become an essential research object in data security research. This study proposes a revolutionary face feature encryption technique that combines picture optimization with cryptography and deep learning (DL) architectures. To improve the security of the key, an optical chaotic map is employed to manage the initial standards of the 5D conservative chaotic method. A safe Crypto General Adversarial neural network and chaotic optical map are provided to finish the course of encrypting and decrypting facial images. The target field is used as a "hidden factor" in the machine learning (ML) method in the encryption method. An encrypted image is recovered to a unique image using a modernization network to achieve picture decryption. A region-of-interest (ROI) network is provided to extract involved items from encrypted images to make data mining easier in a privacy-protected setting. This study’s findings reveal that the recommended implementation provides significantly improved security without sacrificing image quality. Experimental results show that the proposed model outperforms the existing models in terms of PSNR of 92%, RMSE of 85%, SSIM of 68%, MAP of 52%, and encryption speed of 88%.

show abstract

“…An iterative reconstruction algorithm based on a multiscale wavelet domain regularization prior provides improvements in both visual quality and quantitative measurements [9] . A robust compressed sensing image encryption algorithm based on generative adversarial networks, convolutional neural denoising networks, and chaotic systems through the use of CNN denoiser can improve the image quality and visual representation of the final decrypted image [10] .…”

Section: Research Progressmentioning

confidence: 99%

Compressed Sensing: Theory and Applications

Wang

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Compressed sensing is a new technique for solving underdetermined linear systems. Because of its good performance, it has been widely used in academia. It is applied in electrical engineering to recover sparse signals, especially in signal processing. This technique exploits the signal’s sparse nature, allowing the original signals to recover from fewer samples. This paper discusses the fundamentals of compressed sensing theory, the research progress in compressed sensing signal processing, and the applications of compressed sensing theory in nuclear magnetic resonance imaging and seismic exploration acquisition. Compressed sensing allows for the digitization of analogue data with inexpensive sensors and lowers the associated costs of processing, storage, and transmission. Behind its sophisticated mathematical expression, compressed sensing theory contains a subtle idea. Compressed sensing is a novel theory that is an ideal complement and improvement to conventional signal processing. It is a theory with a high vitality level, and its research outcomes may substantially influence signal processing and other fields.

show abstract

A robust compressed sensing image encryption algorithm based on GAN and CNN

Cited by 24 publications

References 44 publications

A Hybrid Domain Image Encryption Algorithm Based on Improved Henon Map

A Hybrid Domain Image Encryption Algorithm Based on Improved Henon Map

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

Compressed Sensing: Theory and Applications

Contact Info

Product

Resources

About