Using of convolutional neural networks for steganalysis of digital images

The article substantiates the relevance of steganalysis, as a determination of the presence of a hidden channel in telecommunication systems, whose nodes exchange digital images. The article deals with the application of convolutional neural networks to solve this problem. It is assumed that the probability of correct image classification using a well-trained convolutional neural network will be comparable or even better than characteristics of statistical algorithms or the RM model. We introduce principles of construction and capabilities of convolutional neural networks in the framework of their applicability to solving the problem of steganalysis. To improve the efficiency and effectiveness of the stegocontainer recognition process, a version of the image classification model for a convolutional neural network is proposed. It is based on combination of several convolutional and fully connected layers. We have developed software for this model version with the ability to train a neural network and evaluate the quality of classification. The analysis of existing software products designed for the task of determining the fact of using steganography in digital images is carried out. The advantage of classifiers based on neural networks in comparison with statistical ones is proved. Using the developed software, an experimental study of classification model on sets of digital images contained in open sources has been carried out. The article presents the results of neural network training, as well as an analysis of the strengths and weaknesses of the selected model.

steganography, steganalysis, digital images, neural network, convolutional layer, fully connected layer, machine learning

1. Boroumand M, Chen M, Fridrich J. Deep Residual Network for Steganalysis of Digital Images. IEEE Transactions on Information Forensics and Security, vol. 14, issue 5, 2019, pp. 1181-1193.

2. Kodovsky J, Fridrich J. Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security, vol. 7, issue 3, 2012, pp. 868-882.

3. Yedroudj M, Comby F, Chaumont M. Yedrouj-Net: An Efficient CNN for Spatial Steganalysis. In Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, 2018, pp. 2092-2096.

4. Lerch-Hostalot D, Megias D. Detection of Classiffer Inconsistencies in Image Steganalysis. In Proc. of the ACM Workshop on Information Hiding and Multimedia Security. 2019, pp. 222-229.

5. Свёрточная нейронная сеть с нуля. Часть 0. Введение [Электронный ресурс] – Режим доступа: URL: https://programforyou.ru/poleznoe/convolutional-network-from-scratch-part-zero-introduction (01.07.2020) / Convolutional neural network from scratch. Part 0. Introduction. URL: https://programforyou.ru/poleznoe/convolutional-network-from-scratch-part-zero-introduction (in Russian).

6. Shafkat I. Intuitively Understanding Convolutions for Deep Learning. URL: https://towardsdatascience.com/intuitively-understanding-convolutions-for-deep-learning-1f6f42faee1 (accessed 06.06.2020).

7. Saha S. A Comprehensive Guide to Convolutional Neural Networks – the ELI5 way. URL: https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53 (accessed 06.06.2020)

8. Yousfi Y, Butora J, Fridrich J, Giboulot Q. Breaking ALASKA: Color Separation for Steganalysis in JPEG Domain. In Proc. of the ACM Workshop on Information Hiding and Multimedia Security, 2019, pp. 138-149.

9. Convolution arithmetic tutorial. URL: http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html (accessed 01.07.2020)

10. Kodovsky J, Fridrich J. Steganalysis of JPEG images using rich models. In Proc. of the SPIE International Conference on Media Watermarking, Security, and Forensics, 2012, paper 8303-8.