Abstract
Mathematical models based on human neuronal network behavior have recently become extremely popular and arouse interest as a solution of various computer vision problems. One of these models—Convolutional Neural Network—has been proven to be very efficient for object recognition problems and resembles principles of visual processing held by animal visual cortex. In this research, we propose a new approach to performing steganalysis on JPEG images using Convolutional Neural Networks. This approach allows to detect hidden embedding without computing features of an image predefined by empirical observations and obtain results comparable to state of the art methods of JPEG image steganalysis.
Similar content being viewed by others
References
Kodovskỳ, J., & Fridrich, J. (2012). Steganalysis of JPEG images using rich models. Media Watermarking Security, and Forensics, 8303.
Chen, C., & Shi, Y.Q. (2008). JPEG image steganalysis utilizing both intrablock and interblock correlations. In IEEE International Symposium on Circuits and Systems, IEEE, 2008.
Qingzhong, L. (2011). Steganalysis of DCT-embedding based adaptive steganography and YASS. In Proceedings of the thirteenth ACM multimedia workshop on Multimedia and security, ACM.
Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems.
Hubel, D.H., & Wiesel, T.N. (1962). Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. The Journal of physiology, 160.1, 106–154.
Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R news 2.3, 18–22.
Vojtech, H., & Fridrich, J. (2014). Challenging the doctrines of JPEG steganography, IST/SPIE Electronic Imaging. International Society for Optics and Photonics.
Bas, P., Filler, T., & Pevn, T. (2011). Break Our Steganographic System: The Ins and Outs of Organizing BOSS. International Workshop on Information Hiding: Springer Berlin Heidelberg.
Lin, T.-Y., & et al. (2014). Microsoft coco: Common objects in context. In European Conference on Computer Vision. Springer International Publishing.
Fridrich, J., Pevn, T., & Kodovsk, J. (2007). Statistically undetectable jpeg steganography: dead ends challenges, and opportunities. In Proceedings of the 9th workshop on Multimedia & security. ACM.
Team, The Theano Development, & et al (2016). Theano: A Python framework for fast computation of mathematical expressions. arXiv preprint. arXiv:1605.02688.
Franois, C. (2015). Keras: Deep learning library for theano and tensorflow.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bashkirova, D. Convolutional Neural Networks for Image Steganalysis. BioNanoSci. 6, 246–248 (2016). https://doi.org/10.1007/s12668-016-0215-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12668-016-0215-z