Hiding Images within Images

We present a system to hide a full color image inside another of the same size with minimal quality loss to either image. Deep neural networks are simultaneously trained to create the hiding and revealing processes and are designed to specifically work as a pair. The system is trained on images drawn randomly from the ImageNet database, and works well on natural images from a wide variety of sources. Beyond demonstrating the successful application of deep learning to hiding images, we examine how the result is achieved and apply numerous transformations to analyze if image quality in the host and hidden image can be maintained. These transformation range from simple image manipulations to sophisticated machine learning-based adversaries. Two extensions to the basic system are presented that mitigate the possibility of discovering the content of the hidden image. With these extensions, not only can the hidden information be kept secure, but the system can be used to hide even more than a single image. Applications for this technology include image authentication, digital watermarks, finding exact regions of image manipulation, and storing meta-information about image rendering and content.

[1]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Jessica J. Fridrich,et al.  Detecting LSB Steganography in Color and Gray-Scale Images , 2001, IEEE Multim..

[3]  Jessica J. Fridrich,et al.  Practical steganalysis of digital images: state of the art , 2002, IS&T/SPIE Electronic Imaging.

[4]  J. Jiang,et al.  Image compression with neural networks - A survey , 1999, Signal Process. Image Commun..

[5]  Edward Y. Chang,et al.  Enhanced perceptual distance functions and indexing for image replica recognition , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Greg Goth,et al.  Steganalysis gets past the hype , 2005, IEEE Distributed Systems Online.

[7]  William F. Friedman.  An Introduction to Methods for the Solution of Ciphers , 2008 .

[8]  Jing Dong,et al.  Deep learning for steganalysis via convolutional neural networks , 2015, Electronic Imaging.

[9]  Feng Zhu,et al.  Efficient feature learning and multi-size image steganalysis based on CNN , 2018, ArXiv.

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

[11]  Benedikt Boehm,et al.  StegExpose - A Tool for Detecting LSB Steganography , 2014, ArXiv.

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

[13]  Rik Van de Walle,et al.  Image scrambling without bandwidth expansion , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[14]  Marc Chaumont,et al.  Securing color information of an image by concealing the color palette , 2013, J. Syst. Softw..

[15]  Jessica J. Fridrich,et al.  Breaking HUGO - The Process Discovery , 2011, Information Hiding.

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

[17]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[18]  Haitham Badi,et al.  Artificial neural network for steganography , 2014, Neural Computing and Applications.

[19]  Svetlana Lazebnik,et al.  Iterative quantization: A procrustean approach to learning binary codes , 2011, CVPR 2011.

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

[21]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[22]  Edith Cohen,et al.  Finding interesting associations without support pruning , 2000, Proceedings of 16th International Conference on Data Engineering (Cat. No.00CB37073).

[23]  Nasir D. Memon,et al.  Steganalysis of audio based on audio quality metrics , 2003, IS&T/SPIE Electronic Imaging.

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

[25]  Konstantinos I. Diamantaras,et al.  Neural Networks and Principal Component Analysis , 2018, Handbook of Neural Network Signal Processing.

[26]  Valero Laparra,et al.  End-to-end Optimized Image Compression , 2016, ICLR.

[27]  Piotr Indyk,et al.  Similarity Search in High Dimensions via Hashing , 1999, VLDB.

[28]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[29]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[30]  Gary C. Kessler,et al.  An Overview of Steganography for the Computer Forensics Examiner , 2004 .

[31]  Shumeet Baluja,et al.  Hiding Images in Plain Sight: Deep Steganography , 2017, NIPS.

[32]  Kevin Curran,et al.  Digital image steganography: Survey and analysis of current methods , 2010, Signal Process..

[33]  Shumeet Baluja,et al.  Waveprint: Efficient wavelet-based audio fingerprinting , 2008, Pattern Recognit..

[34]  Xuelong Li,et al.  Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Bhupendra Verma,et al.  Neural network based steganography algorithm for still images , 2010, INTERACT-2010.

[36]  Marc Chaumont,et al.  Wavelet-based data hiding of DEM in the context of real-time 3D visualization , 2007, Electronic Imaging.

[37]  Niels Provos,et al.  Hide and Seek: An Introduction to Steganography , 2003, IEEE Secur. Priv..

[38]  Robert Jarusek,et al.  Robust steganographic method based on unconventional approach of neural networks , 2018, Appl. Soft Comput..

[39]  V. Kavitha,et al.  Neural Based Steganography , 2004, PRICAI.

[40]  Marc Chaumont,et al.  Protecting the Color Information by Hiding it , 2009 .

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

[42]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[43]  Lucas Theis,et al.  Lossy Image Compression with Compressive Autoencoders , 2017, ICLR.

[44]  Shawn D. Dickman.  An Overview of Steganography , 2007 .

[45]  Omaima N. A. AL-Allaf,et al.  Hiding an Image inside another Image using Variable-Rate Steganography , 2013 .

[46]  Robert Jarusek,et al.  Neural Network Approach to Image Steganography Techniques , 2015, MENDEL.

[47]  Tomás Pevný,et al.  Statistically undetectable jpeg steganography: dead ends challenges, and opportunities , 2007, MM&Sec.

[48]  Paul W. Munro,et al.  Principal Components Analysis Of Images Via Back Propagation , 1988, Other Conferences.

[49]  Lubomir D. Bourdev,et al.  Real-Time Adaptive Image Compression , 2017, ICML.

[50]  Mansour Jamzad,et al.  Estimating Watermarking Capacity in Gray Scale Images Based on Image Complexity , 2010, EURASIP J. Adv. Signal Process..

[51]  Marc Chaumont,et al.  Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch , 2015, Media Watermarking, Security, and Forensics.

[52]  Anil K. Jain,et al.  Hiding Biometric Data , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[53]  Marc Chaumont,et al.  Yedroudj-Net: An Efficient CNN for Spatial Steganalysis , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[54]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[55]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[56]  Gang Wang,et al.  Learning Image Similarity from Flickr Groups Using Fast Kernel Machines , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[57]  David Minnen,et al.  Variational image compression with a scale hyperprior , 2018, ICLR.

[58]  Guanrong Chen,et al.  Cryptanalysis of an Image Scrambling Scheme Without Bandwidth Expansion , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[59]  A. S. Brandão,et al.  Artificial Neural Networks Applied to Image Steganography , 2016, IEEE Latin America Transactions.