Steganalyzing Images of Arbitrary Size with CNNs

Convolutional neural networks offer much more accurate detection of steganography than the outgoing paradigm classifiers trained on rich representations of images. While training a CNN is scalable with respect to the size of the training set, one cannot directly train on images that are too large due to the memory limitations of current GPUs. Most leading network architectures for steganalysis today require the input image to be a small tile with 256× 256 or 512× 512 pixels. Because detecting the presence of steganographic embedding changes really means detecting a very weak noise signal added to the cover image, resizing an image before presenting it to a CNN would be highly suboptimal. Applying the tile detector on disjoint segments of a larger image and fusing the results bring a plethora of new problems of how to properly fuse the outputs. In this paper, we propose a different solution to this problem based on modifying an existing leading network architecture for steganalysis in the spatial domain, the YeNet, to output statistical moments of feature maps to the fullyconnected classifier part of the network. On experiments in which we adjust the payload with image size according the square root law for constant statistical detectability, we demonstrate that the proposed architecture can be trained to steganalyze images of various sizes without any or only a small loss with respect to detectors trained for a fixed image size.

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

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

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

[4]  Jiaxing Zhang,et al.  Scale-Invariant Convolutional Neural Networks , 2014, ArXiv.

[5]  Tomás Pevný,et al.  The square root law of steganographic capacity , 2008, MM&Sec '08.

[6]  Tomás Pevný,et al.  Optimizing pooling function for pooled steganalysis , 2015, 2015 IEEE International Workshop on Information Forensics and Security (WIFS).

[7]  Jessica J. Fridrich,et al.  Practical strategies for content-adaptive batch steganography and pooled steganalysis , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

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

[10]  Guanshuo Xu,et al.  Deep Convolutional Neural Network to Detect J-UNIWARD , 2017, IH&MMSec.

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

[12]  Tomás Pevný,et al.  Batch steganography in the real world , 2012, MM&Sec '12.

[13]  Jiangqun Ni,et al.  Deep Learning Hierarchical Representations for Image Steganalysis , 2017, IEEE Transactions on Information Forensics and Security.

[14]  J. Nadal,et al.  Self-Similarity Properties of Natural Images Resemble Those of Turbulent Flows , 1998, cond-mat/0107314.

[15]  N. Parga,et al.  Ju l 2 00 1 The multi-fractal structure of contrast changes in natural images : from sharp edges to textures , 2008 .

[16]  Mo Chen,et al.  JPEG-Phase-Aware Convolutional Neural Network for Steganalysis of JPEG Images , 2017, IH&MMSec.

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

[18]  Andrew D. Ker.  Batch Steganography and Pooled Steganalysis , 2006, Information Hiding.

[19]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[20]  Andrew D. Ker.  Locally Square Distortion and Batch Steganographic Capacity , 2009, Int. J. Digit. Crime Forensics.

[21]  Andrew D. Ker.  Perturbation Hiding and the Batch Steganography Problem , 2008, Information Hiding.

[22]  Yun Q. Shi,et al.  Ensemble of CNNs for Steganalysis: An Empirical Study , 2016, IH&MMSec.

[23]  Andrew D. Ker,et al.  Steganalysis with mismatched covers: do simple classifiers help? , 2012, MM&Sec '12.

[24]  Rémi Cogranne,et al.  A sequential method for online steganalysis , 2015, 2015 IEEE International Workshop on Information Forensics and Security (WIFS).

[25]  Andrew D. Ker.  Batch steganography and the threshold game , 2007, Electronic Imaging.

[26]  Jessica J. Fridrich,et al.  Steganalysis of JPEG images using rich models , 2012, Other Conferences.

[27]  Jessica J. Fridrich,et al.  The square root law of steganographic capacity for Markov covers , 2009, Electronic Imaging.

[28]  Yi Zhang,et al.  Steganalysis of Adaptive JPEG Steganography Using 2D Gabor Filters , 2015, IH&MMSec.

[29]  Andrew D. Ker.  A Capacity Result for Batch Steganography , 2007, IEEE Signal Processing Letters.

[30]  Jessica Fridrich,et al.  Modeling and Extending the Ensemble Classifier for Steganalysis of Digital Images Using Hypothesis Testing Theory , 2015, IEEE Transactions on Information Forensics and Security.

[31]  Ruderman,et al.  Multiscaling and information content of natural color images , 2000, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.