A robust and secure immensely random GAN based image encryption mechanism

Singh, Om Dev; Dhall, Sangeeta; Malik, Anjali; Gupta, Shailender

doi:10.1007/s11042-022-14000-w

Cited by 7 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This GAN is then utilized to provide encryption keys as input to newly designed S-boxes and P-boxes. The proposed GAN-based algorithm in [41] is shown to carry out encryption both at the bit-level and byte-level, performing very well in comparison to counterpart algorithms from the literature. In [37], the authors re-imagine 2D images as circular objects, or rotors, which can be rotated in clockwise or anti-clockwise directions, such that these rotations can be used to substitute the image pixels.…”

Section: Related Workmentioning

confidence: 96%

“…The main advantage of this work is the improved efficiency achieved through the use of quantum methods over traditional ones. A very recent work by the authors of [41] develops an unsupervised deep learning algorithm trained on chaotic maps to build a generative adversarial network (GAN). This GAN is then utilized to provide encryption keys as input to newly designed S-boxes and P-boxes.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

R ³—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

Gabr,

Korayem,

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This work proposes a novel image encryption algorithm that integrates unique image transformation techniques with the principles of chaotic and hyper-chaotic systems. By harnessing the unpredictable behavior of the Chua system and the hyper-chaotic nature of the Chen system, the algorithm carries out rescaling, rotation, and randomization on the target image. The intrinsic unpredictability and sensitivity to initial conditions of these chaotic systems endow the encryption algorithm with an expansive key space of 2 5208 . This feature not only bolsters its resilience against brute-force attacks but also magnifies its overall security profile. The algorithm's efficiency is evident in its rapid computational speed and lean resource consumption, making it suitable for real-time applications. To gauge its robustness, a battery of rigorous tests and analyses, spanning differential attacks, statistical attacks, and brute-force assaults, were employed. The results validate its ability to resist a diverse spectrum of threats. With its expansive key space, exceptional efficiency, and sturdy defenses, the proposed algorithm emerges as a potential cornerstone for safeguarding digital images in arenas like secure communication, data storage, and multimedia transmission. In sum, this research pushes the boundaries of high-security image encryption methodologies, catering to the burgeoning demands of the digital age.

show abstract

Section: Related Workmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

R ³—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

Gabr,

Korayem,

Chen

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The main advantage of this work is the improved efficiency achieved through the use of quantum methods over traditional ones. A very recent work by the authors of [32] develops an unsupervised deep learning algorithm trained on chaotic maps to build a Generative Adversarial Network (GAN). This GAN is then utilized to provide encryption keys as input to newly designed S-boxes and P-boxes.…”

Section: Related Literaturementioning

confidence: 99%

“…This ensures a high level of security, as any attempt to decrypt the image without the exact key sequence will fail. Moreover, the use of rotation mechanisms in PRNGs can also improve the diffusion and confusion properties of the encryption algorithm [32]. Diffusion aims to spread the influence of one plaintext digit over many ciphertext digits so that the original image (the plaintext) is effectively "hidden" in the encrypted image (the ciphertext).…”

Section: Introductionmentioning

confidence: 99%

R3−Rescale, Rotate and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyperchaotic Systems

Gabr,

Korayem,

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>This work proposes a novel image encryption algorithm that combines unique image transformation techniques with the principles of chaotic and hyperchaotic systems. The proposed algorithm performs rescaling, rotation, and randomization on the target image by exploiting the unpredictable behavior of the Chua system and the hyperchaotic nature of the Chen system. These chaotic systems' unpredictability and sensitivity to initial conditions are utilized to create an encryption algorithm that provides an extensive key space of 2^(5208), contributing to its robustness against brute-force attacks and amplifying its overall security. The efficiency of the algorithm is demonstrated in its computational speed and minimal resource consumption, making it practical for real-time applications. A series of rigorous tests and analyses were conducted to evaluate the algorithm's performance, substantiating its capability to withstand a wide array of attacks, including differential attacks, statistical attacks, and brute-force attacks. With its vast key space, high efficiency, and robust resistance to attacks, the proposed algorithm shows potential as a vital tool for securing digital images in various applications, such as secure communication, data storage, and multimedia transmission. This research contributes to the ongoing development and evolution of high-security image encryption methodologies, meeting the escalating demand for advanced security in the digital information era.</p>

show abstract

“…Ding et al [19] proposed a key generation network based on a generative adversarial network (GAN), which transferred the medical image to the private key and obtained a ciphertext image by XOR with the plaintext image. Singh et al [20] enhanced the encryption effect by combining the GAN-based generated key with further scramble and diffusion. Apart from GAN, Zhou et al [21] presented a color image encryption system that used a long short-term memory (LSTM) network to train chaotic signals and applied them to encrypt color images.…”

Section: Introductionmentioning

confidence: 99%

A Novel Medical Image Encryption Scheme Based on Deep Learning Feature Encoding and Decoding

Long,

Chen,

Liu

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Medical image encryption is essential to protect the privacy and confidentiality of patients' medical records. Deep learning-based encryption, which leverages the nonlinear characteristics of neural networks, has emerged as a promising new method for protecting medical images. In this paper, we present insights into deep learning-based medical image encryption and propose a novel end-to-end medical image encryption scheme based on these insights that leverage feature encoding and decoding for encrypting and decrypting images. Firstly, we explore a method that combines keys generated by the Logistic Map with encoded plaintext image features to improve network diffusion performance. Secondly, we employ a reversible neural network to enhance plaintext image reconstruction while maintaining encryption effectiveness. Finally, we propose a series of novel loss functions to measure the cost with the ideal cryptographic algorithm and continuously optimize our network. Experimental results demonstrate that our scheme improves the performance of image encryption and decryption and resists brute force attacks, statistical attacks, noise and cropping attacks.

show abstract

A robust and secure immensely random GAN based image encryption mechanism

Cited by 7 publications

References 40 publications

R ³—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

R ³—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

R3−Rescale, Rotate and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyperchaotic Systems

A Novel Medical Image Encryption Scheme Based on Deep Learning Feature Encoding and Decoding

Contact Info

Product

Resources

About

A robust and secure immensely random GAN based image encryption mechanism

Cited by 7 publications

References 40 publications

R 3—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

R 3—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

R3−Rescale, Rotate and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyperchaotic Systems

A Novel Medical Image Encryption Scheme Based on Deep Learning Feature Encoding and Decoding

Contact Info

Product

Resources

About

R ³—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems

R ³—Rescale, Rotate, and Randomize: A Novel Image Cryptosystem Utilizing Chaotic and Hyper-Chaotic Systems