Steganographic generative adversarial networks

Volkhonskiy, Denis; Nazarov, Ivan; Burnaev, Evgeny

doi:10.1117/12.2559429

Cited by 134 publications

(120 citation statements)

References 10 publications

(15 reference statements)

Supporting

Mentioning

120

Contrasting

Order By: Relevance

“…Volkhonskiy et al [79] proposed the application of GAN to steganography. They construct a special generator for creating cover-image, synthetic images generated by this generator are less susceptible to steganalysis compared to covers.…”

Section: Generating Cover Imagesmentioning

confidence: 99%

Recent Advances of Image Steganography With Generative Adversarial Networks

et al. 2020

View full text Add to dashboard Cite

In the past few years, the Generative Adversarial Network (GAN) which proposed in 2014 has achieved great success. GAN has achieved many research results in the field of computer vision and natural language processing. Image steganography is dedicated to hiding secret messages in digital images, and has achieved the purpose of covert communication. Recently, research on image steganography has demonstrated great potential for using GAN and neural networks. In this paper we review different strategies for steganography such as cover modification, cover selection and cover synthesis by GANs, and discuss the characteristics of these methods as well as evaluation metrics and provide some possible future research directions in image steganography.

show abstract

Section: Generating Cover Imagesmentioning

confidence: 99%

Recent Advances of Image Steganography With Generative Adversarial Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…El-Emam [30] and Saleema [31] work on using neural networks to refine the embedded image generated via traditional steganography methods, i.e., LSB method. Volkhonskiy's [32] and Shi's [33] work focus on generating secure cover images for traditional steganography methods to apply image steganography. Baluja [34] is working on the same field as StegNet.…”

Section: Neural Network For Steganographymentioning

confidence: 99%

StegNet: Mega Image Steganography Capacity with Deep Convolutional Network

Yang

2018

Future Internet

100

View full text Add to dashboard Cite

Traditional image steganography often leans interests towards safely embedding hidden information into cover images with payload capacity almost neglected. This paper combines recent deep convolutional neural network methods with image-into-image steganography. It successfully hides the same size images with a decoding rate of 98.2% or bpp (bits per pixel) of 23.57 by changing only 0.76% of the cover image on average. Our method directly learns end-to-end mappings between the cover image and the embedded image and between the hidden image and the decoded image. We further show that our embedded image, while with mega payload capacity, is still robust to statistical analysis.

show abstract

“…This approach generates embedded messages that are more secure against steganalysis using standard cover modification algorithms. Similar to [12], Shi, et al [14] introduced a new GAN design with improved the convergence speed, training stability and image quality. Abadi [15] used adversarial training to teach two neural networks to encrypt a short message that would fool a discriminator.…”

Section: Related Workmentioning

confidence: 99%

Generative Steganography by Sampling

Zhang

Yan

et al. 2019

IEEE Access

View full text Add to dashboard Cite

In this paper, a novel data-driven information hiding scheme called "generative steganography by sampling" (GSS) is proposed. Unlike in traditional modification-based steganography, in our method the stego image is directly sampled by a powerful generator: no explicit cover is used. Both parties share a secret key used for message embedding and extraction. The Jensen-Shannon divergence is introduced as a new criterion for evaluating the security of generative steganography. Based on these principles, we propose a simple practical generative steganography method that uses semantic image inpainting. The message is written in advance to an uncorrupted region that needs to be retained in the corrupted image. Then, the corrupted image with the secret message is fed into a Generator trained by a generative adversarial network (GAN) for semantic completion. Message loss and prior loss terms are proposed for penalizing message extraction error and unrealistic stego image. In our design, we first train a generator whose training target is the generation of new data samples from the same distribution as that of existing training data. Next, for the trained generator, backpropagation to the message and prior loss are introduced to optimize the coding of the input noise data for the generator. The presented experiments demonstrate the potential of the proposed framework based on both qualitative and quantitative evaluations of the generated stego images. INDEX TERMS Generative adversarial network, Image inpainting, Steganography

show abstract

Steganographic generative adversarial networks

Cited by 134 publications

References 10 publications

Recent Advances of Image Steganography With Generative Adversarial Networks

Recent Advances of Image Steganography With Generative Adversarial Networks

StegNet: Mega Image Steganography Capacity with Deep Convolutional Network

Generative Steganography by Sampling

Contact Info

Product

Resources

About