Advertisement

A Deep Residual Multi-scale Convolutional Network for Spatial Steganalysis

  • Shiyang Zhang
  • Hong ZhangEmail author
  • Xianfeng Zhao
  • Haibo Yu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11378)

Abstract

Recent studies have indicated that Convolutional Neural Network (CNN), incorporated with certain domain knowledge, is capable of achieving competitive performances on discriminating trivial perturbation introduced by spatial steganographic schemes. In this paper, we propose a deep residual multi-scale convolutional network model, which outperforms several CNN-based steganalysis schemes and hand-crafted rich models. Compared to CNN-based steganalyzers proposed in recent studies, our model has a deeper network structure and it is integrated with a series of proven elements and complicated convolutional modules. With the intention of abstracting features from various dimensions, multi-scale convolutional modules are designed in three different ways. Besides, inspired by the idea of residual learning, shortcut components are adopted in the proposed model. Extensive experiments with BOSSbase v1.01 and LIRMMBase are carried out, which demonstrates that our network is able to detect multiple state-of-the-art spatial embedding schemes with different payloads.

Keywords

Spatial steganalysis Convolutional Neural Network Deep residual network Multi-scale convolutional module 

Notes

Acknowledgments

This work was supported by NSFC under 61802393, U1636102, U1736214 and 61872356, National Key Technology R&D Program under 2016YFB0801003 and 2016QY15Z2500, and Project of Beijing Municipal Science & Technology Commission under Z181100002718001.

References

  1. 1.
    Bas, Patrick, Filler, Tomáš, Pevný, Tomáš: “Break our steganographic system”: the ins and outs of organizing BOSS. In: Filler, Tomáš, Pevný, Tomáš, Craver, Scott, Ker, Andrew (eds.) IH 2011. LNCS, vol. 6958, pp. 59–70. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-24178-9_5CrossRefGoogle Scholar
  2. 2.
    Bianchini, M., Scarselli, F.: On the complexity of neural network classifiers: a comparison between shallow and deep architectures. IEEE Trans. Neural Netw. Learn. Syst. 25(8), 1553–1565 (2014)CrossRefGoogle Scholar
  3. 3.
    Denemark, T., Sedighi, V., Holub, V., Cogranne, R., Fridrich, J.: Selection-channel-aware rich model for steganalysis of digital images. In: Proceedings of the 2014 IEEE International Workshop on Information Forensics and Security, Atlanta, GA, USA, pp. 48–53 (2014)Google Scholar
  4. 4.
    Filler, T., Judas, J., Fridrich, J.: Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans. Inf. Forensics Secur. 6(3–2), 920–935 (2011)CrossRefGoogle Scholar
  5. 5.
    Fridrich, J., Kodovský, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)CrossRefGoogle Scholar
  6. 6.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 770–778 (2016)Google Scholar
  7. 7.
    Holub, V., Fridrich, J.: Designing steganographic distortion using directional filters. In: Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security, Costa Adeje, Tenerife, Spain, pp. 234–239 (2012)Google Scholar
  8. 8.
    Holub, V., Fridrich, J.: Random projections of residuals for digital image steganalysis. IEEE Trans. Inf. Forensics Secur. 8(12), 1996–2006 (2013)CrossRefGoogle Scholar
  9. 9.
    Holub, V., Fridrich, J., Denemark, T.: Universal distortion function for steganography in an arbitrary domain. EURASIP J. Inf. Secur. 2014, 1 (2014)CrossRefGoogle Scholar
  10. 10.
    Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp. 2261–2269 (2017)Google Scholar
  11. 11.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, Lille, France, pp. 448–456 (2015)Google Scholar
  12. 12.
    Pevný, T., Filler, T., Bas, P.: Using high-dimensional image models to perform highly undetectable steganography. In: Proceedings of the 12th International Workshop on Information Hiding, Calgary, AB, Canada, pp. 161–177 (2010)Google Scholar
  13. 13.
    Pibre, L., Pasquet, J., Ienco, D., Chaumont, M.: Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch. In: Proceedings of the 2016 IS&T, Electronic Imaging, Media Watermarking, Security, and Forensics, San Francisco, CA, USA, pp. 1–11 (2016)Google Scholar
  14. 14.
    Qian, Y., Dong, J., Wang, W., Tan, T.: Deep learning for steganalysis via convolutional neural networks. In: Proceedings of the 2015 IS&T, Electronic Imaging, Media Watermarking, Security, and Forensics, San Francisco, CA, USA, p. 94090J (2015)Google Scholar
  15. 15.
    Qian, Y., Dong, J., Wang, W., Tan, T.: Learning and transferring representations for image steganalysis using convolutional neural network. In: Proceedings of the 2016 IEEE International Conference on Image Processing, Phoenix, AZ, USA, pp. 2752–2756 (2016)Google Scholar
  16. 16.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014). http://arxiv.org/abs/1409.1556
  17. 17.
    Sun, S., Chen, W., Wang, L., Liu, X., Liu, T.: On the depth of deep neural networks: a theoretical view. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA, pp. 2066–2072 (2016)Google Scholar
  18. 18.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the 31st AAAI Conference on Artificial Intelligence, San Francisco, CA, USA, pp. 4278–4284 (2017)Google Scholar
  19. 19.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 1–9 (2015)Google Scholar
  20. 20.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 2818–2826 (2016)Google Scholar
  21. 21.
    Tan, S., Li, B.: Stacked convolutional auto-encoders for steganalysis of digital images. In: Proceedings of the 2014 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Chiang Mai, Thailand, pp. 1–4 (2014)Google Scholar
  22. 22.
    Wu, S., Zhong, S., Liu, Y.: Steganalysis via deep residual network. In: Proceedings of the 22nd IEEE International Conference on Parallel and Distributed Systems, Wuhan, China, pp. 1233–1236 (2016)Google Scholar
  23. 23.
    Wu, S., Zhong, S., Liu, Y.: Residual convolution network based steganalysis with adaptive content suppression. In: Proceedings of the 2017 IEEE International Conference on Multimedia and Expo, Hong Kong, China, pp. 241–246 (2017)Google Scholar
  24. 24.
    Wu, S., Zhong, S., Liu, Y.: Deep residual learning for image steganalysis. Multimedia Tools Appl. 77(9), 10437–10453 (2018)CrossRefGoogle Scholar
  25. 25.
    Xu, G.: Deep convolutional neural network to detect J-UNIWARD. In: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security, Philadelphia, PA, USA, pp. 67–73 (2017)Google Scholar
  26. 26.
    Xu, G., Wu, H., Shi, Y.Q.: Ensemble of CNNs for steganalysis: an empirical study. In: Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security, Vigo, Galicia, Spain, pp. 103–107 (2016)Google Scholar
  27. 27.
    Xu, G., Wu, H., Shi, Y.: Structural design of convolutional neural networks for steganalysis. IEEE Signal Process. Lett. 23(5), 708–712 (2016)CrossRefGoogle Scholar
  28. 28.
    Yang, J., Liu, K., Kang, X., Wong, E.K., Shi, Y.: Steganalysis based on awareness of selection-channel and deep learning. In: Proceedings of the 16th International Workshop on Digital Forensics and Watermarking, Magdeburg, Germany, pp. 263–272 (2017)Google Scholar
  29. 29.
    Ye, J., Ni, J., Yi, Y.: Deep learning hierarchical representations for image steganalysis. IEEE Trans. Inf. Forensics Secur. 12(11), 2545–2557 (2017)CrossRefGoogle Scholar
  30. 30.
    Yedroudj, M., Chaumont, M., Comby, F.: How to augment a small learning set for improving the performances of a CNN-based steganalyzer? CoRR abs/1801.04076 (2018). http://arxiv.org/abs/1801.04076
  31. 31.
    Yedroudj, M., Comby, F., Chaumont, M.: Yedrouj-net: an efficient CNN for spatial steganalysis. CoRR abs/1803.00407 (2018). http://arxiv.org/abs/1803.00407
  32. 32.
    Yuan, Y., Lu, W., Feng, B., Weng, J.: Steganalysis with CNN using multi-channels filtered residuals. In: Proceedings of the 3rd International Conference on Cloud Computing and Security, Nanjing, China, pp. 110–120 (2017)Google Scholar
  33. 33.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs/1212.5701 (2012). http://arxiv.org/abs/1212.5701
  34. 34.
    Zhu, X., Liu, J., Wang, J., Li, C., Lu, H.: Sparse representation for robust abnormality detection in crowded scenes. Pattern Recogn. 47(5), 1791–1799 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Shiyang Zhang
    • 1
    • 2
  • Hong Zhang
    • 1
    • 2
    Email author
  • Xianfeng Zhao
    • 1
    • 2
  • Haibo Yu
    • 1
    • 2
  1. 1.State Key Laboratory of Information Security, Institute of Information EngineeringChinese Academy of SciencesBeijingChina
  2. 2.School of Cyber SecurityUniversity of Chinese Academy of SciencesBeijingChina

Personalised recommendations