A Generative Steganography Method Based on WGAN-GP

With the development of Generative Adversarial Networks (GAN), GAN-based steganography and steganalysis techniques have attracted much attention from researchers. In this paper, we propose a novel image steganography method without modification based on Wasserstein GAN Gradient Penalty (WGAN-GP). The proposed architecture has a generative network, a discriminative network, and an extractor network. The Generator is used to generate the cover image (also is the stego image), and the Extractor is used to extract secret information. During the process of stego image generation, no modification operations are required. To make full use of the learning ability of convolutional neural networks and GAN, we synchronized the training of Generator and Extractor. Experiment results show that the proposed method has the advantages of higher recovery accuracy and higher training efficiency.

[1]  Kai Liu,et al.  Spatial Image Steganography Based on Generative Adversarial Network , 2018, ArXiv.

[2]  Jessica J. Fridrich,et al.  Content-Adaptive Steganography by Minimizing Statistical Detectability , 2016, IEEE Transactions on Information Forensics and Security.

[3]  Bin Li,et al.  Investigation on Cost Assignment in Spatial Image Steganography , 2014, IEEE Transactions on Information Forensics and Security.

[4]  Li Fei-Fei,et al.  HiDDeN: Hiding Data With Deep Networks , 2018, ECCV.

[5]  Bin Li,et al.  Automatic Steganographic Distortion Learning Using a Generative Adversarial Network , 2017, IEEE Signal Processing Letters.

[6]  Shigeru Kuriyama,et al.  Data-Embeddable Texture Synthesis , 2007, Smart Graphics.

[7]  Hang Zhou,et al.  Defining Cost Functions for Adaptive JPEG Steganography at the Microscale , 2019, IEEE Transactions on Information Forensics and Security.

[8]  Jessica J. Fridrich,et al.  Multivariate gaussian model for designing additive distortion for steganography , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Xingming Sun,et al.  Coverless Image Steganography Without Embedding , 2015, ICCCS.

[10]  Bin Li,et al.  A Novel Image Steganography Method via Deep Convolutional Generative Adversarial Networks , 2018, IEEE Access.

[11]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[12]  George Danezis,et al.  Generating steganographic images via adversarial training , 2017, NIPS.

[13]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[14]  Tomás Pevný,et al.  Using High-Dimensional Image Models to Perform Highly Undetectable Steganography , 2010, Information Hiding.

[15]  Jessica J. Fridrich,et al.  Rich Models for Steganalysis of Digital Images , 2012, IEEE Transactions on Information Forensics and Security.

[16]  Jessica J. Fridrich,et al.  Universal distortion function for steganography in an arbitrary domain , 2014, EURASIP Journal on Information Security.

[17]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[18]  Jessica Fridrich,et al.  Steganography in Digital Media: References , 2009 .

[19]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.