Abstract
Recent studies have proved a well-designed convolutional neural network (CNN) is a good steganalytic tool. In this paper, based on the previous work, we report a method using segmented subimages to improve the testing accuracy of CNN for steganalysis. In training phase, a CNN is trained on training set of whole image. In testing phase, for a given testing image, a sliding window is employed to segment the whole testing image into subimages. Each subimage is feed into the trained CNN respectively to obtain a subdecision. The final decision is obtained through majority vote. Experiments show that the proposed method achieves significant improvement on testing accuracy when detecting S-UNIWARD and HILL under payload of 0.4 bpp, whereas the time efficiency is only slightly worse compared with previous work.
Supported by 1. National Natural Science Foundation of China, NO. 61601517. 2. Foundation of Science and Technology on Information Assurance Laboratory, NO. KJ-15-106.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Pevný, T., Bas, P., Fridrich, J.: Steganalysis by subtractive pixel adjacency matrix. IEEE Trans. Inf. Forensics Secur. 5(2), 215–224 (2010)
Fridrich, J., Kodovský, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)
Holub, V., Fridrich, J.: Random projections of residuals for digital image steganalysis. IEEE Trans. Inf. Forensics Secur. 8(12), 1996–2006 (2013)
Denemark, T., Sedighi, V., Holub, V., Cogranne, R., Fridrich, J.: Selection-channel-aware rich model for steganalysis of digital images. In: IEEE International Workshop on Information Forensics and Security, pp. 48–53. IEEE (2014)
Kodovský, J., Fridrich, J., Holub, V.: Ensemble classifiers for steganalysis of digital media. IEEE Trans. Inf. Forensics Secur. 7(2), 432–444 (2012)
Tan, S., Li, B.: Stacked convolutional auto-encoders for steganalysis of digital images. In: Signal and Information Processing Association Annual Summit and Conference, pp. 1–4. IEEE, Chiang Mai (2014)
Ker, A.D., Böhme, R.: Revisiting weighted stego-image steganalysis. In: Security, Forensics, Steganography, and Watermarking of Multimedia Contents X, vol. 6819, p. 681905. International Society for Optics and Photonics (2008)
Qian, Y., Dong, J., Wang, W., Tan, T.: Deep learning for steganalysis via convolutional neural networks. In: Media Watermarking, Security, and Forensics, vol. 9409, p. 94090J. International Society for Optics and Photonics (2015)
Xu, G., Wu, H.Z., Shi, Y.Q.: Structural design of convolutional neural networks for steganalysis. IEEE Signal Process. Lett. 23(5), 708–712 (2016)
Holub, V., Fridrich, J., Denemark, T.: Universal distortion function for steganography in an arbitrary domain. EURASIP J. Inf. Secur. 2014(1), 1–13 (2014)
Li, B., Wang, M., Huang, J., Li, X.: A new cost function for spatial image steganography. In: IEEE International Conference on Image Processing, pp. 4206–4210. IEEE (2014)
Zeng, J., Tan, S., Li, B., Huang, J.: Large-scale JPEG image steganalysis using hybrid deep-learning framework. IEEE Trans. Inf. Forensics Secur. 13(5), 1200–1214 (2018)
Tang, W., Tan, S., Li, B., Huang, J.: Automatic steganographic distortion learning using a generative adversarial network. IEEE Signal Process. Lett. 24(10), 1547–1551 (2017)
Chen, M., Sedighi, V., Boroumand, M., Fridrich, J.: JPEG-phase-aware convolutional neural network for steganalysis of JPEG images. In: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security, pp. 75–84. ACM (2017)
Wu, S., Zhong, S., Liu, Y.: Deep residual learning for image steganalysis. Multimedia Tools Appl., 1–17 (2017)
Wu, S., Zhong, S.H., Liu, Y.: Residual convolution network based steganalysis with adaptive content suppression. In: IEEE International Conference on Multimedia and Expo, pp. 241–246. IEEE (2017)
Ye, J., Ni, J., Yi, Y.: Deep learning hierarchical representations for image steganalysis. IEEE Trans. Inf. Forensics Secur. 12(11), 2545–2557 (2017)
Xu, G.: Deep convolutional neural network to detect J-UNIWARD. In: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security, pp. 67–73. ACM (2017)
Wu, S., Zhong, S.H., Liu, Y.: A Novel Convolutional Neural Network for Image Steganalysis with Shared Normalization. arXiv preprint arXiv:1711.07306 (2017)
Yang, J., Shi, Y.Q., Wong, E.K., Kang, X.: JPEG Steganalysis Based on DenseNet. arXiv preprint arXiv:1711.09335 (2017)
Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: Convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on Multimedia, pp. 675–678. ACM (2014)
Bas, P., Filler, T., Pevný, T.: “Break our steganographic system”: the ins and outs of organizing BOSS. In: Filler, T., Pevný, T., Craver, S., Ker, A. (eds.) IH 2011. LNCS, vol. 6958, pp. 59–70. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24178-9_5
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, Y., Xu, X., Song, H., Tang, G., Yang, S. (2018). Improving Testing Accuracy of Convolutional Neural Network for Steganalysis Using Segmented Subimages. In: Sun, X., Pan, Z., Bertino, E. (eds) Cloud Computing and Security. ICCCS 2018. Lecture Notes in Computer Science(), vol 11066. Springer, Cham. https://doi.org/10.1007/978-3-030-00015-8_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-00015-8_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00014-1
Online ISBN: 978-3-030-00015-8
eBook Packages: Computer ScienceComputer Science (R0)