Reversible Image Steganography Scheme Based on a U-Net Structure

Duan, Xintao; Jia, Kai; Li, Baoxia; Guo, Daidou; Zhang, En; Qin, Chuan

doi:10.1109/access.2019.2891247

Cited by 139 publications

(137 citation statements)

References 35 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Xintao architecture. At start, in double traineeship, the training deep neural network contains an invisible network and a recover network; then, the transmitter uses the lurking network to imply the confidential picture into a whole picture without any moderation and send it to the recipient [15]. Zhiguo Qu, Zhenwen CHENG and Xiaojun Wang proposed two different implying style.…”

Section: Related Workmentioning

confidence: 99%

Hide text depending on the three channels of pixels in color images using the modified LSB algorithm

Neamah¹,

Abed²,

Abbood³

2020

IJECE

View full text Add to dashboard Cite

At the moment, with the great development of information and communications technology, the transfer of confidential and sensitive data through public communications such as the Internet is very difficult to keep them from hackers and attackers. Therefore, it is necessary to work on the development of new and innovative ways to transfer such information and protect it to ensure that it reaches the desired goal. The goal of a new technique to hide information design not only hides the secret message behind the center cover, but it also provides increased security. The most common way to transfer important and confidential data is through embedding it into cover medium files in a way that does not affect the accuracy of the carrier file, which is known as hiding. In this paper, encryption and concealment techniques were used to protect data transferred from attackers. The proposed method relied on encryption of confidential information using the encryption key and the Xnor gate, after which the encrypted information was hidden in a color image using the LSB algorithm. The method of concealment depends on the extraction of chromatic channels of three RGB for each pixel and specifying the channel in which the bit of the encryption message will be hidden. Some metrics have been adopted to measure the quality of the resulting picture after hiding as PSNR and MSE, and achieve good results.

show abstract

Section: Related Workmentioning

confidence: 99%

Hide text depending on the three channels of pixels in color images using the modified LSB algorithm

Neamah¹,

Abed²,

Abbood³

2020

IJECE

View full text Add to dashboard Cite

show abstract

“…Deep neural network approach to embed secret information inside the digital images ensuring the secure steganography. In contrast to previous traditional studies many deep learning-based frameworks have been developed successfully that allow researchers to hide large information inside the natural images without possible eavesdropper [56][57][58][59], [72][73][74]. The primarily application of deep learning to steganography was GAN based steganography [56].…”

Section: Deep Learning Based Image Steganographymentioning

confidence: 99%

“…Furthermore, proposed network uses three sub-networks which requires more computations & GPU memory and it also takes more time to hide the secret information. Recently in 2019 Duan et al [57] proposed a new reversible steganography framework based on U-Net structure. Their network composed of two networks, hiding network called U-Net and an extraction network.…”

Section: Deep Learning Based Image Steganographymentioning

confidence: 99%

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

2020

KSII TIIS

View full text Add to dashboard Cite

Steganalysis & steganography have witnessed immense progress over the past few years by the advancement of deep convolutional neural networks (DCNN). In this paper, we analyzed current research states from the latest image steganography and steganalysis frameworks based on deep learning. Our objective is to provide for future researchers the work being done on deep learning-based image steganography & steganalysis and highlights the strengths and weakness of existing up-to-date techniques. The result of this study opens new approaches for upcoming research and may serve as source of hypothesis for further significant research on deep learning-based image steganography and steganalysis. Finally, technical challenges of current methods and several promising directions on deep learning steganography and steganalysis are suggested to illustrate how these challenges can be transferred into prolific future research avenues.

show abstract

“…One common point in the schemes designed in [ 8 , 9 , 10 , 14 , 23 ] is that they use convolutional neural networks to embed only a secret image in the carrier image. The solution we designed is to embed two secret images into the carrier image and realize high-capacity steganography under the premise of ensuring steganography security.…”

Section: Steganocnn Architecturementioning

confidence: 99%

SteganoCNN: Image Steganography with Generalization Ability Based on Convolutional Neural Network

Duan

Liu

Gou

et al. 2020

Entropy

Self Cite

View full text Add to dashboard Cite

Image-to-image steganography is hiding one image in another image. However, hiding two secret images into one carrier image is a challenge today. The application of image steganography based on deep learning in real-life is relatively rare. In this paper, a new Steganography Convolution Neural Network (SteganoCNN) model is proposed, which solves the problem of two images embedded in a carrier image and can effectively reconstruct two secret images. SteganoCNN has two modules, an encoding network, and a decoding network, whereas the decoding network includes two extraction networks. First, the entire network is trained end-to-end, the encoding network automatically embeds the secret image into the carrier image, and the decoding network is used to reconstruct two different secret images. The experimental results show that the proposed steganography scheme has a maximum image payload capacity of 47.92 bits per pixel, and at the same time, it can effectively avoid the detection of steganalysis tools while keeping the stego-image undistorted. Meanwhile, StegaoCNN has good generalization capabilities and can realize the steganography of different data types, such as remote sensing images and aerial images.

show abstract

Reversible Image Steganography Scheme Based on a U-Net Structure

Cited by 139 publications

References 35 publications

Hide text depending on the three channels of pixels in color images using the modified LSB algorithm

Hide text depending on the three channels of pixels in color images using the modified LSB algorithm

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

SteganoCNN: Image Steganography with Generalization Ability Based on Convolutional Neural Network

Contact Info

Product

Resources

About