Steganography in stylized images

Abstract. We propose a steganographic scheme for stylized images. Given a natural image, an image style transfer algorithm is executed twice to produce two similar stylized images with different parameters. One of them is used for embedding and another one is employed as a reference. For the cover image, embedding costs are assigned to measure the detection risk of the modifications. Each embedding cost is then asymmetrically adjusted into two polarity costs to further measure the detection risk of different modification polarities with the guidance of the reference image. After embedding with syndrome-trellis coding, the difference of the stegoimage and the reference image is minimized, which results in a high undetectability against steganalysis. Experimental results also prove that the proposed scheme performs much better than the existing steganographic methods when examined by modern steganalytic tools.

[1]  Jessica J. Fridrich,et al.  Practical methods for minimizing embedding impact in steganography , 2007, Electronic Imaging.

[2]  Hong Zhang,et al.  Improving the Robustness of Adaptive Steganographic Algorithms Based on Transport Channel Matching , 2019, IEEE Transactions on Information Forensics and Security.

[3]  Andrea Vedaldi,et al.  Understanding deep image representations by inverting them , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Tomás Pevný,et al.  "Break Our Steganographic System": The Ins and Outs of Organizing BOSS , 2011, Information Hiding.

[5]  Shumeet Baluja,et al.  Hiding Images within Images , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  陈世峰.  Style Transfer via Image Component Analysis , 2013 .

[7]  Weiming Zhang,et al.  On the fault-tolerant performance for a class of robust image steganography , 2018, Signal Process..

[8]  Chuan Li,et al.  Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[10]  Jessica J. Fridrich,et al.  Rich model for Steganalysis of color images , 2014, 2014 IEEE International Workshop on Information Forensics and Security (WIFS).

[11]  Xinpeng Zhang,et al.  Robust Batch Steganography in Social Networks With Non-Uniform Payload and Data Decomposition , 2018, IEEE Access.

[12]  Jessica J. Fridrich,et al.  Designing steganographic distortion using directional filters , 2012, 2012 IEEE International Workshop on Information Forensics and Security (WIFS).

[13]  Michael Ashikhmin,et al.  Fast Texture Transfer , 2003, IEEE Computer Graphics and Applications.

[14]  Xinpeng Zhang,et al.  Efficient Steganographic Embedding by Exploiting Modification Direction , 2006, IEEE Communications Letters.

[15]  Jessica J. Fridrich,et al.  Digital image steganography using universal distortion , 2013, IH&MMSec '13.

[16]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[17]  Weiming Zhang,et al.  Maximizing Steganographic Embedding Efficiency by Combining Hamming Codes and Wet Paper Codes , 2008, Information Hiding.

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

[19]  Xinpeng Zhang,et al.  Distortion Function for Spatial Image Steganography Based on the Polarity of Embedding Change , 2016, IWDW.

[20]  Jessica J. Fridrich,et al.  Ensemble Classifiers for Steganalysis of Digital Media , 2012, IEEE Transactions on Information Forensics and Security.

[21]  Xiangyang Luo,et al.  Selection of Rich Model Steganalysis Features Based on Decision Rough Set $\alpha$ -Positive Region Reduction , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[22]  Jiangqun Ni,et al.  Model-based image steganography using asymmetric embedding scheme , 2018, J. Electronic Imaging.

[23]  Jorge Nocedal,et al.  Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization , 1997, TOMS.

[24]  Zhenxing Qian,et al.  On Improving Distortion Functions for JPEG Steganography , 2018, IEEE Access.

[25]  Jessica J. Fridrich,et al.  Matrix embedding for large payloads , 2006, IEEE Trans. Inf. Forensics Secur..

[26]  Xinpeng Zhang,et al.  Towards Robust Image Steganography , 2019, IEEE Transactions on Circuits and Systems for Video Technology.

[27]  Leon A. Gatys,et al.  Texture Synthesis Using Convolutional Neural Networks , 2015, NIPS.

[28]  Bin Li,et al.  A new cost function for spatial image steganography , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[29]  Leon A. Gatys,et al.  Image Style Transfer Using Convolutional Neural Networks , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[31]  Jia Deng,et al.  A large-scale hierarchical image database , 2009, CVPR 2009.

[32]  Alexei A. Efros,et al.  Image quilting for texture synthesis and transfer , 2001, SIGGRAPH.

[33]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[34]  Weiming Zhang,et al.  Steganalysis of HUGO steganography based on parameter recognition of syndrome-trellis-codes , 2016, Multimedia Tools and Applications.

[35]  Bin Li,et al.  A Strategy of Clustering Modification Directions in Spatial Image Steganography , 2015, IEEE Transactions on Information Forensics and Security.

[36]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).