Yun-Qing Shi

Jianhua Yang, Yi Liao, Fei Shang et al.

A great challenge to steganography has arisen with the wide application of steganalysis methods based on convolutional neural networks (CNNs). To this end, embedding cost learning frameworks based on generative adversarial networks (GANs) have been proposed and achieved success for spatial steganography. However, the application of GAN to JPEG steganography is still in the prototype stage; its anti-detectability and training efficiency should be improved. In conventional steganography, research has shown that the side-information calculated from the precover can be used to enhance security. However, it is hard to calculate the side-information without the spatial domain image. In this work, an embedding cost learning framework for JPEG Steganography via a Generative Adversarial Network (JS-GAN) has been proposed, the learned embedding cost can be further adjusted asymmetrically according to the estimated side-information. Experimental results have demonstrated that the proposed method can automatically learn a content-adaptive embedding cost function, and use the estimated side-information properly can effectively improve the security performance. For example, under the attack of a classic steganalyzer GFR with quality factor 75 and 0.4 bpnzAC, the proposed JS-GAN can increase the detection error 2.58% over J-UNIWARD, and the estimated side-information aided version JS-GAN(ESI) can further increase the security performance by 11.25% over JS-GAN.

Wenkang Su, Jiangqun Ni, Yuanfeng Pan et al.

Recent advances on adaptive steganography show that the performance of image steganographic communication can be improved by incorporating the non-additive models that capture the dependences among adjacent pixels. In this paper, a Gaussian Markov Random Field model (GMRF) with four-element cross neighborhood is proposed to characterize the interactions among local elements of cover images, and the problem of secure image steganography is formulated as the one of minimization of KL-divergence in terms of a series of low-dimensional clique structures associated with GMRF by taking advantages of the conditional independence of GMRF. The adoption of the proposed GMRF tessellates the cover image into two disjoint subimages, and an alternating iterative optimization scheme is developed to effectively embed the given payload while minimizing the total KL-divergence between cover and stego, i.e., the statistical detectability. Experimental results demonstrate that the proposed GMRF outperforms the prior arts of model based schemes, e.g., MiPOD, and rivals the state-of-the-art HiLL for practical steganography, where the selection channel knowledges are unavailable to steganalyzers.

Jianhua Yang, Kai Liu, Xiangui Kang et al.

With the recent development of deep learning on steganalysis, embedding secret information into digital images faces great challenges. In this paper, a secure steganography algorithm by using adversarial training is proposed. The architecture contain three component modules: a generator, an embedding simulator and a discriminator. A generator based on U-NET to translate a cover image into an embedding change probability is proposed. To fit the optimal embedding simulator and propagate the gradient, a function called Tanh-simulator is proposed. As for the discriminator, the selection-channel awareness (SCA) is incorporated to resist the SCA based steganalytic methods. Experimental results have shown that the proposed framework can increase the security performance dramatically over the recently reported method ASDL-GAN, while the training time is only 30% of that used by ASDL-GAN. Furthermore, it also performs better than the hand-crafted steganographic algorithm S-UNIWARD.

Ye Yao, Weitong Hu, Wei Zhang et al.

Computer-generated graphics (CGs) are images generated by computer software. The~rapid development of computer graphics technologies has made it easier to generate photorealistic computer graphics, and these graphics are quite difficult to distinguish from natural images (NIs) with the naked eye. In this paper, we propose a method based on sensor pattern noise (SPN) and deep learning to distinguish CGs from NIs. Before being fed into our convolutional neural network (CNN)-based model, these images---CGs and NIs---are clipped into image patches. Furthermore, three high-pass filters (HPFs) are used to remove low-frequency signals, which represent the image content. These filters are also used to reveal the residual signal as well as SPN introduced by the digital camera device. Different from the traditional methods of distinguishing CGs from NIs, the proposed method utilizes a five-layer CNN to classify the input image patches. Based on the classification results of the image patches, we deploy a majority vote scheme to obtain the classification results for the full-size images. The~experiments have demonstrated that (1) the proposed method with three HPFs can achieve better results than that with only one HPF or no HPF and that (2) the proposed method with three HPFs achieves 100\% accuracy, although the NIs undergo a JPEG compression with a quality factor of 75.

Jianhua Yang, Yun-Qing Shi, Edward K. Wong et al.

Different from the conventional deep learning work based on an images content in computer vision, deep steganalysis is an art to detect the secret information embedded in an image via deep learning, pose challenge of detection weak information invisible hidden in a host image thus learning in a very low signal-to-noise (SNR) case. In this paper, we propose a 32- layer convolutional neural Networks (CNNs) in to improve the efficiency of preprocess and reuse the features by concatenating all features from the previous layers with the same feature- map size, thus improve the flow of information and gradient. The shared features and bottleneck layers further improve the feature propagation and reduce the CNN model parameters dramatically. Experimental results on the BOSSbase, BOWS2 and ImageNet datasets have showed that the proposed CNN architecture can improve the performance and enhance the robustness. To further boost the detection accuracy, an ensemble architecture called as CNN-SCA-GFR is proposed, CNN-SCA- GFR is also the first work to combine the CNN architecture and conventional method in the JPEG domain. Experiments show that it can further lower detection errors. Compared with the state-of-the-art method XuNet [1] on BOSSbase, the proposed CNN-SCA-GFR architecture can reduce detection error rate by 5.67% for 0.1 bpnzAC and by 4.41% for 0.4 bpnzAC while the number of training parameters in CNN is only 17% of what used by XuNet. It also decreases the detection errors from the conventional method SCA-GFR by 7.89% for 0.1 bpnzAC and 8.06% for 0.4 bpnzAC, respectively.

Han-Zhou Wu, Hong-Xia Wang, Yun-Qing Shi

In recent years, due to the powerful abilities to deal with highly complex tasks, the artificial neural networks (ANNs) have been studied in the hope of achieving human-like performance in many applications. Since the ANNs have the ability to approximate complex functions from observations, it is straightforward to consider the ANNs for steganography. In this paper, we aim to implement the well-known LSB substitution and matrix coding steganography with the feed-forward neural networks (FNNs). Our experimental results have shown that, the used FNNs can achieve the data embedding operation of the LSB substitution and matrix coding steganography. For steganography with the ANNs, though there may be some challenges to us, it would be very promising and valuable to pay attention to the ANNs for steganography, which may be a new direction for steganography.

Han-Zhou Wu, Hong-Xia Wang, Yun-Qing Shi

This paper presents a novel reversible data hiding (RDH) algorithm for gray-scaled images, in which the prediction-error of prediction error (PPE) of a pixel is used to carry the secret data. In the proposed method, the pixels to be embedded are firstly predicted with their neighboring pixels to obtain the corresponding prediction errors (PEs). Then, by exploiting the PEs of the neighboring pixels, the prediction of the PEs of the pixels can be determined. And, a sorting technique based on the local complexity of a pixel is used to collect the PPEs to generate an ordered PPE sequence so that, smaller PPEs will be processed first for data embedding. By reversibly shifting the PPE histogram (PPEH) with optimized parameters, the pixels corresponding to the altered PPEH bins can be finally modified to carry the secret data. Experimental results have implied that the proposed method can benefit from the prediction procedure of the PEs, sorting technique as well as parameters selection, and therefore outperform some state-of-the-art works in terms of payload-distortion performance when applied to different images.