Digital Cardan Grille: A Modern Approach for Information Hiding

In this paper, a new framework for construction of Cardan grille for information hiding is proposed. Based on the semantic image inpainting technique, the stego image are driven by secret messages directly. A mask called Digital Cardan Grille (DCG) for determining the hidden location is introduced to hide the message. The message is written to the corrupted region that needs to be filled in the corrupted image in advance. Then the corrupted image with secret message is fed into a Generative Adversarial Network (GAN) for semantic completion. The adversarial game not only reconstruct the corrupted image, but also generate a stego image which contains the logic rationality of image content. The experimental results verify the feasibility of the proposed method.

[1]  Minh N. Do,et al.  Semantic Image Inpainting with Perceptual and Contextual Losses , 2016, ArXiv.

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

[3]  Mário Marques Fernandes,et al.  ADVANCES IN FACE DETECTION AND FACIAL IMAGE ANALYSIS , 2018 .

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

[5]  Mauro Barni.  Steganography in Digital Media: Principles, Algorithms, and Applications (Fridrich, J. 2010) [Book Reviews] , 2011, IEEE Signal Processing Magazine.

[6]  Gang Hua,et al.  Labeled Faces in the Wild: A Survey , 2016 .

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

[8]  Lakhmi C. Jain,et al.  Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the Thirteenth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2017, August, 12-15, 2017, Matsue, Shimane, Japan, Part II , 2018, Intelligent Information Hiding and Multimedia Signal Processing.

[9]  Zhenxing Qian,et al.  Robust Steganography Using Texture Synthesis , 2017 .

[10]  Xiaogang Jin,et al.  Hidden message in a deformation-based texture , 2014, The Visual Computer.

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

[12]  A. F. Adams,et al.  The Survey , 2021, Dyslexia in Higher Education.

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

[14]  Kuo-Chen Wu,et al.  Steganography Using Reversible Texture Synthesis , 2015, IEEE Transactions on Image Processing.

[15]  Jing Dong,et al.  SSGAN: Secure Steganography Based on Generative Adversarial Networks , 2017, PCM.

[16]  Jia Liu,et al.  Generative Steganography with Kerckhoffs' Principle based on Generative Adversarial Networks , 2017, ArXiv.

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

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

[19]  Shigeru Kuriyama,et al.  Texture Synthesis for Mobile Data Communications , 2009, IEEE Computer Graphics and Applications.

[20]  Phil Sallee,et al.  Model-Based Steganography , 2003, IWDW.

[21]  Evgeny Burnaev,et al.  Steganographic generative adversarial networks , 2017, International Conference on Machine Vision.

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

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