Hiding Images in Plain Sight: Deep Steganography

Steganography is the practice of concealing a secret message within another, ordinary, message. Commonly, steganography is used to unobtrusively hide a small message within the noisy regions of a larger image. In this study, we attempt to place a full size color image within another image of the same size. 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 carefully examine how the result is achieved and explore extensions. Unlike many popular steganographic methods that encode the secret message within the least significant bits of the carrier image, our approach compresses and distributes the secret image's representation across all of the available bits.

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

[2]  Chuohao Yeo,et al.  Intrinsic images decomposition using a local and global sparse representation of reflectance , 2011, CVPR 2011.

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

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

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

[6]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

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

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

[10]  T. Ens,et al.  Blind signal separation : statistical principles , 1998 .

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

[12]  Mostafa Rahmani,et al.  Steganography: Dct Coefficient Replacement Method and Compare With JSteg Algorithm , 2012 .

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

[14]  Andrew B. Watson,et al.  DCT quantization matrices visually optimized for individual images , 1993, Electronic Imaging.

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

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

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

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

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

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

[21]  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 , 2016, Media Watermarking, Security, and Forensics.

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

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

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

[25]  Terrence J. Sejnowski,et al.  The “independent components” of natural scenes are edge filters , 1997, Vision Research.

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

[27]  George Danezis,et al.  ste-GAN-ography: Generating Steganographic Images via Adversarial Training , 2017, ArXiv.

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

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