Abstract
Image steganalysis identifies whether a secret message is hidden in an image. Conventional steganalytic methods require processes to extract discriminative statistical features from images and classify them. Convolutional neural networks (CNN) are particularly effective at conducting those processes. However, since the hidden message was too weak to be detected, existing CNN-based steganalytic methods needed to adopt preprocessing filters to increase the strength of the hidden message. Then, development focused on improved network structures and preprocessing filters. In this paper, we propose a different approach to CNN-based image steganalysis. We embed additional data in an input image and use two images (i.e., the original input image and its stego image with additional embedded data) as input. This is based on an assumption that pixel variations due to the additional embedded data would be sufficient to identify images with and without a secret message. We also propose two variants of conventional CNNs for image steganalysis, named dual channel CNN and dual network CNN, to input two images. We conducted various experiments using the proposed CNNs. The experimental results prove that the assumption holds, and the additional input could provide useful information to improve the performance of conventional CNN-based steganalytic methods. Depending on the strength of the hidden message, the proposed approach could improve the identification rate by up to 6% for S-UNIWARD, an adaptive steganographic method.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
Xu and Wu’s CNN [32] is the most basic, and most conventional CNNs are modifications of this network. Therefore, in this experiment, it was used as the base CNN.
References
Balasubramanian C, Selvakumar S, Geetha S (2014) High payload image steganography with reduced distortion using octonary pixel pairing scheme. Multimed Tools Appl:2223–2245
Bas P, Filler T, Pevny T (2011) Break our steganographic system – the ins and outs of organizing BOSS. International Workshop on Information Hiding 6958:59–70
Bhattacharya T, Dey N, Chaudhuri SRB (2012) A session based multiple image hiding technique using DWT and DCT. Int J Comput Appl 38(5):398–409
Boroumand M, Chen M, Fridrich J (2019) Deep residual network for steganalysis of digital images. IEEE Transactions on Information Forensics and Security 14(5):1181–1193
Cancelli G, Doerr G, Cox IJ, Barni M (2008) Detection of ±1 LSB steganography based on the amplitude of histogram local extrema. ICIP:1288–1291
Chan C-K, Cheng LM (2004) Hiding data in images by simple LSB substitution. Pattern Recogn 37(3):469–474
Chang K, Chang C, Huang PS, Tu T (2008) A novel image steganographic method using tri-way pixel-value differencing. J Multimed 3(2):37–44
Cheddad A, Condell J, Curran K, Mc Kevitt P (2010) Digital image steganography: survey and analyses of current methods. Signal Process 90(3):727–752
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Dabeer O, Sullivan K, Madhow U, Chandrasekaran S, Manjunath BS (2004) Detection of hiding in the least significant bit. IEEE Trans Signal Process 52(10):3046–3058
Dorgham O, Al-Rahamneh B, Almomani A, Al-Hadidi M, Khatatneh KF (2018) Enhancing the security of exchanging and storing DICOM medical images on the cloud. International Journal of Cloud Applications and Computing 8(1):154–172
Fridrich J, Du R, Long M (2000) Steganalysis of LSB encoding in color images. ICME:1279–1282
Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security 7(3):868–882
Gul G, Kurugollu F (2011) A new methodology in steganalysis: breaking highly undetectable steganography (HUGO). International Workshop on Information Hiding:71–84
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. CVPR
Ho TK (1995) Random decision forests. Proceedings of 3rd International Conference on Document Analysis and Recognition, Montreal, vol. 1, pp. 275–282
Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. International Workshop on Information Forensics and Security
Holub V, Fridrich J, Denemark T (2014) Universal distortion function for stegangography in an arbitrary domain. EURASIP Journal of Information Security
Karampidis K, Kavallieratou E, Papadourakis G (2018) A review of image steganalysis techniques for digital forensics. Journal of Information Security and Applications 40:217–235
Ker AD (2005) A general framework for structural analysis of LSB replacement. International Workshop on Information Hiding 3727:296–311
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. NIPS:1097–1105
Kumar A (2019) Design of secure image fusion technique using cloud for privacy-preserving and copyright protection. International Journal of Cloud Applications and Computing 9(3):22–36
Li B, Wei W, Ferreira A, Tan S (2018) ReST-Net: diverse activation modules and parallel subnets-based CNN for spatial image steganalysis. IEEE Signal Processing Letters 25(5):650–654
Neeta D, Snehal K, Jacobs D (2007) Implementation of LSB steganography and its evaluation for various bits. International Conference on Digital Information Management:173–178
Pevny T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Transactions on Information Forensics and Security 5(2):215–224
Qian N (1999) On the momentum term in gradient descent learning algorithms. Neural Netw 12:145–151
Steganographic algorithms. http://dde.binghamton.edu/download/stego_algorithms/. Accessed on 19 Jan 2019
Tang W, Li B, Tan S, Barni M, Juang J (2019) CNN-based adversarial embedding for image steganography. IEEE Transactions on Information Forensics and Security 14(8):2074–2087
TensorFlow. https://www.tensorflow.org/. Accessed on 19 Jan 2019
Wu D, Tsai W (2003) A steganographic method for images by pixel-value differencing. Pattern Recognition Letters 24:1613–1326
Wu S, Zhong S, Liu Y (2018) Deep residual learning for image steganalysis. Multimed Tools Appl 77(9):10437–10453
Xu G, Wu H (2016) Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters 23(5):708–712
Ye J, Ni J, Yi Y (2017) Deep learning hierarchical representations for image steganalysis. IEEE Transactions on Information Forensics and Security 12(11):2545–2557
Yedroudj M, Comby F, Chaumont M (2018) Yedroudj-Net: an efficient CNN for spatial steganalysis. ICASSP:15–20
Yu X, Tan H, Liang H, Li CT, Liao G (2018) A multi-task learning CNN for image steganalysis. 10th IEEE International Workshop on Information Forensics and Security
Yuan Y, Lu W, Feng B, Weng J (2017) Steganalysis with CNN using multi-channels filtered residuals. ICCCS:110–120
Zeiler MD (2012) ADADELTA: An adaptive learning rate method. arXiv:1212.5701
Zhang T, Zhang H, Wang R, Wu Y (2019) A new JPEG image steganalysis technique combining rich model features and convolutional neural networks. Mathematical Biosciences and Engineering 16(5):4069–4081
Acknowledgements
This work was supported by the research fund of Signal Intelligence Research Center supervised by Defense Acquisition Program Administration and Agency for Defense Development of Korea.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kim, J., Park, H. & Park, JI. CNN-based image steganalysis using additional data embedding. Multimed Tools Appl 79, 1355–1372 (2020). https://doi.org/10.1007/s11042-019-08251-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08251-3