Hiding Images within Images

Baluja, Shumeet

doi:10.1109/tpami.2019.2901877

Cited by 192 publications

(144 citation statements)

References 43 publications

Supporting

Mentioning

142

Contrasting

Order By: Relevance

“…The framework of the entire model is shown in Figure 2 . We are different from the solution [ 24 ]. In our SteganoCNN model, the preparation network is removed, and three different hidden networks ((b), (c), (d)) are used to train the entire network.…”

Section: Steganocnn Architecturementioning

confidence: 99%

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

Duan

Liu

Gou

et al. 2020

Entropy

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

Section: Steganocnn Architecturementioning

confidence: 99%

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

Duan

Liu

Gou

et al. 2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Baluja et al [ 13 ] proposed the framework for hiding the image in the image. It consists of three parts of the network: preprocessing network, hiding network, and extraction network.…”

Section: Related Knowledgementioning

confidence: 99%

“…In this work, we use an improved [ 13 ] framework, but removed the preprocessing network, and replaced the hidden network with our improved deep separable convolutional Xception network [ 14 ] in order to achieve the same size as the cover image and the secret image with the same number of channels (three channel color image or one channel gray image) can be perfectly embedded in the cover image with only slight pixel distortion. The secret image can be steganographically written in all bits and channels of the cover image.…”

Section: Introductionmentioning

confidence: 99%

High-Capacity Image Steganography Based on Improved Xception

Duan

Gou

Liu

et al. 2020

Sensors

View full text Add to dashboard Cite

The traditional cover modification steganography method only has low steganography ability. We propose a steganography method based on the convolutional neural network architecture (Xception) of deep separable convolutional layers in order to solve this problem. The Xception architecture is used for image steganography for the first time, which not only increases the width of the network, but also improves the adaptability of network expansion, and adds different receiving fields to carry out multi-scale information in it. By introducing jump connections, we solved the problems of gradient dissipation and gradient descent in the Xception architecture. After cascading the secret image and the mask image, high-quality images can be reconstructed through the network, which greatly improves the speed of steganography. When hiding, only the secret image and the cover image are cascaded, and then the secret image can be embedded in the cover image through the hidden network in order to obtain the secret image. After extraction, the secret image can be reconstructed by bypassing the secret image through the extraction network. The results show that the results that are obtained by our model have high peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), and the average high load capacity is 23.96 bpp (bit per pixel), thus realizing large-capacity image steganography surgery.

show abstract

“…In [17]- [19], the text is converted to binary data, and then the position of the LSB is automatically selected by the neural network for embedding. In contrast, in our work, the difference between us and [20] is that the preparation network is removed, and the hidden network uses Full Convolution Dense Connection Network (FC-DenseNet) [21]. In our work, first, the secret image and the carrier image are encoded as a stego-image via a hidden network, and secondly, the stego-image is decoded into a secret image via a decoding network.…”

Section: Introductionmentioning

confidence: 97%

High-Capacity Image Steganography Based on Improved FC-DenseNet

et al. 2020

View full text Add to dashboard Cite

Aiming at the problem that the traditional steganography based on carrier modification has the low steganographic capacity, a steganographic scheme based on Fully Convolutional Dense Connection Network (FC-DenseNet) is proposed. Since FC-DenseNet can effectively overcome the problems of gradient dissipation and gradient explosion, and a large number of features are multiplexed, the cascaded secret image and carrier image can reconstruct good image quality after entering the network. Effectively improve steganographic capacity. First, we reset the number of input channels of the first convolution block of FC-DenseNet and the number of output channels of the last convolution block and deleted the LogSoftmax() function. On the sender side, after the concatenated secret image and carrier image pass through the hidden network FC-DenseNet, the secret image is embedded in the carrier image to obtain a stego-image. At the receiving side, the extraction network reconstructs the secret image from the stegoimage. Experimental results show that our proposed steganography scheme not only has a high Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity(SSIM) but also can realize large-capacity image steganography, with an average image payload capacity of 23.96 bit per pixel.

show abstract

Hiding Images within Images

Cited by 192 publications

References 43 publications

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

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

High-Capacity Image Steganography Based on Improved Xception

High-Capacity Image Steganography Based on Improved FC-DenseNet

Contact Info

Product

Resources

About