An Efficient JPEG Steganalysis Model Based on Deep Learning

  • Lin GanEmail author
  • Yang Cheng
  • Yu Yang
  • Linfeng Shen
  • Zhexuan Dong
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 895)


Convolutional neural networks (CNN) have gained an overwhelming advantage in many domains of pattern recognition. CNN’s excellent data learning ability and automatic feature extraction ability are urgently needed for image steganalysis research. However, the application of CNN in image steganalysis is still in its infancy, especially in the field of JPEG steganalysis. This paper presents an efficient CNN-based JPEG steganographic analysis model which is called JPEGCNN. According to the pixel neighborhood model, JPEGCNN calculates the pixel residual as a network input with a 3 × 3 kernel function. In this way, JPEGCNN not only solves the problem that direct analysis of DCT coefficients is greatly affected by image content, but also solves the problem that larger kernel functions such as 5 × 5 do not effectively capture neighborhood correlation changes. Compared with the JPEG steganographic analysis model HCNN proposed by the predecessors, JPEGCNN is a lightweight structure. The JPEGCNN training parameters are about 60,000, and the number of parameters is much lower than the number of parameters of the HCNN. At the same time of structural simplification, the simulation results show that JPEGCNN still maintains accuracy close to HCNN.


Steganalysis Convolutional neural network Transform domain 



This work is supported by the National Key R&D Program of China (No. 2017YFB0802703) and Open Foundation of Guizhou Provincial Key Laboratory of Public Big Data (No. 2018BDKFJJ014).


  1. 1.
    Pevný, T., Filler, T., Bas, P.: Using High-Dimensional Image Models to Perform Highly Undetectable Steganography. Springer, Berlin (2010)Google Scholar
  2. 2.
    Holub, V., Fridrich, J.: Designing steganographic distortion using directional filters. In: IEEE International Workshop on Information Forensics and Security (WIFS), vol. 2, pp. 234–239 (2012).
  3. 3.
    Holub, V., Fridrich, J.: Digital image steganography using universal distortion. In: Proceedings of the First ACM Workshop on Information Hiding and Multimedia Security, Montpellier, 17–19 June 2013, pp. 59–68 (2013).
  4. 4.
    Sedighi, V., Cogranne, R., Fridrich, J.: Content-adaptive steganography by minimizing statistical detectability. IEEE Trans. Inf. Forensics Secur. 11, 221–234 (2016). Scholar
  5. 5.
    Li, B., Wang, M., Li, X., Tan, S., Huang, J.: A strategy of clustering modification directions in spatial image steganography. IEEE Trans. Inf. Forensics Secur. 10, 1905–1917 (2015). Scholar
  6. 6.
    Fridrich, J., et al.: Breaking HUGO—the process discovery. In: Information Hiding-international Conference, vol. 6958, pp. 85–101 (2011).
  7. 7.
    Jan, K., Fridrich, J.: Steganalysis in high dimensions: fusing classifiers built on random subspaces. In: Proceedings of SPIE—The International Society for Optical Engineering, vol. 7880, pp. 181–197 (2011)Google Scholar
  8. 8.
    Fridrich, J., Kodovsky, J.: Rich Models for Steganalysis of Digital Images. IEEE Trans. Inf. Forensics Secur. 7, 868–882 (2012)CrossRefGoogle Scholar
  9. 9.
    Holub, V., Fridrich, J.: Random projections of residuals for digital image steganalysis. IEEE Trans. Inf. Forensics Secur. 8, 1996–2006 (2013). Scholar
  10. 10.
    Qian, Y., Dong, J., Wang, W., Tan, T.: Deep learning for steganalysis via convolutional neural networks. In: Proceedings of the SPIE, Media Watermarking, Security, and Forensics 2015, pp. 94 090 J–1–94 090 J–10 (2015)Google Scholar
  11. 11.
    Pibre, L., Jérôme, P., 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 source-mismatch. In: Proceedings of the Media Watermarking, Security, and Forensics, Part of IS&T International Symposium on Electronic Imaging (EI 2016), February 2016Google Scholar
  12. 12.
    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)CrossRefGoogle Scholar
  13. 13.
    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
  14. 14.
    Zeng, J., Tan, S.: Large-scale JPEG steganalysis using hybrid deep-learning framework. IEEE Trans. Inf. Forensics Secur. 13(5), 1200–1214 (2016)CrossRefGoogle Scholar
  15. 15.
    Holub, V., Fridrich, J.: Low-complexity features for JPEG steganalysis using undecimated DCT. IEEE Trans. Inf. Forensics Secur. 10(2), 219–228 (2015)CrossRefGoogle Scholar
  16. 16.
    Holub, V., Fridrich, J.: Phase-aware projection model for steganalysis of JPEG images. In: Proceedings of the SPIE, Electronic Imaging, Media Watermarking, Security, and Forensics XVII, vol. 9409 (2015)Google Scholar
  17. 17.
    Bas, P., Filler, T., Pevný, T.: Break our steganographic system: the ins and outs of organizing boss. In: Information Hiding, pp. 59–70. Springer (2011)Google Scholar
  18. 18.
    Holub, V., Fridrich, J., Denemark, T.: Universal distortion function for steganography in an arbitrary domain. EURASIP J. Inf. Secur. 2014(1), 1–13 (2014)CrossRefGoogle Scholar
  19. 19.
    Zeiler, M.D.: ADADELTA: An adaptive learning rate method. https://arXiv:1212.5701 (2012)
  20. 20.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Aistats, vol. 9, pp. 249–256 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Lin Gan
    • 1
    Email author
  • Yang Cheng
    • 1
  • Yu Yang
    • 1
    • 2
  • Linfeng Shen
    • 1
  • Zhexuan Dong
    • 1
  1. 1.School of Cyberspace SecurityBeijing University of Posts and TelecommunicationsBeijingChina
  2. 2.Guizhou Provincial Key Laboratory of Public Big DataGuiZhou UniversityGuizhouChina

Personalised recommendations