Generative Steganography with Kerckhoffs' Principle based on Generative Adversarial Networks

The distortion in steganography comes from the modification or recoding on the cover image during the embedding process. The changes of the cover always leave the steganalyzer with possibility of discriminating. Therefore, we propose to use a cover to send out secret messages without any modification by training the cover image to generate the secret messages. To ensure the security of such a generative scheme, we require the generator to meet Kerckhoffs' principle. Based on above proposal, we propose generative steganography with Kerckhoffs' principle (GSK) in this letter. In GSK, we use a generator based on generative adversarial networks (GAN) to output the secret messages if and only if the data-hiding key and the cover image are both inputted. Without the data-hiding key or the cover image, only meaningless results would be outputted. We detail the framework and the internal structure of GSK. In our training procedures, there are two GANs, Key-GAN and Cover-GAN, designed to work jointly making the generated results under the control of the data-hiding key and the cover image. Experimental results concentrate on the training process and the working performance of GSK which demonstrate that GSK can use any image to realize steganography with Kerckhoffs' principle without any modification.

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

[2]  Jing Dong,et al.  Learning and transferring representations for image steganalysis using convolutional neural network , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[3]  Bin Li,et al.  A Survey on Image Steganography and Steganalysis , 2011, J. Inf. Hiding Multim. Signal Process..

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

[5]  Jessica J. Fridrich,et al.  Minimizing Additive Distortion in Steganography Using Syndrome-Trellis Codes , 2011, IEEE Transactions on Information Forensics and Security.

[6]  Yun Q. Shi,et al.  Structural Design of Convolutional Neural Networks for Steganalysis , 2016, IEEE Signal Processing Letters.

[7]  C. Fontaine,et al.  Watermarking security: theory and practice , 2005, IEEE Transactions on Signal Processing.

[8]  François Cayre,et al.  Kerckhoffs-Based Embedding Security Classes for WOA Data Hiding , 2008, IEEE Transactions on Information Forensics and Security.

[9]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[10]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[11]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[12]  Martín Abadi,et al.  Learning to Protect Communications with Adversarial Neural Cryptography , 2016, ArXiv.

[13]  Peter P. Swire.  A Model for When Disclosure Helps Security: What Is Different About Computer and Network Security? , 2004, J. Telecommun. High Technol. Law.