Journal of Real-Time Image Processing

, Volume 14, Issue 1, pp 223–236 | Cite as

Highly accurate real-time image steganalysis based on GPU

  • Chao XiaEmail author
  • Qingxiao Guan
  • Xianfeng Zhao
  • Chengduo Zhao
Special Issue Paper


With the development of steganography, it is required to build high-dimensional feature spaces to detect those sophisticated steganographic schemes. However, the huge time cost prevents the practical deployment of high-dimensional features for steganalysis. SRM and DCTR are important steganalysis feature sets in spatial domain and JPEG domain, respectively. It is necessary to accelerate the extraction of DCTR and SRM to make them more usable in practice, especially for some real-time applications. In this paper, both DCTR and SRM are implemented on the GPU device to exploit the parallel power of the GPU and some optimization methods are presented. For implementation of DCTR, we first utilize the separability and symmetry of two-dimensional discrete cosine transform in decompression and convolution. Then, in order to make phase-aware histograms favorable for parallel GPU processing, we convert them into ordinary 256-dimensional histograms. For SRM, in computing residuals, we specify the computation sequence and spilt the inseparable two-dimensional kernel into several row vectors. When computing the four-dimensional co-occurrences, we convert them into one-dimensional histograms which are more suitable for parallel computing. The experimental results show that the proposed methods can greatly accelerate the extraction of DCTR and SRM, especially for images of large size. Our methods can be applied to the real-time steganalysis system.


Steganalysis DCTR features SRM features CUDA GPU programming 


  1. 1.
    Chen, K., Lin, C., Zhong, S., Guo, L.: A parallel SRM feature extraction algorithm for steganalysis based on GPU architecture. In: Sixth International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), 2014, pp. 178–182 (2014)Google Scholar
  2. 2.
    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 (WIFS), 2014, pp. 48–53 (2014)Google Scholar
  3. 3.
    Filler, T., Judas, J., Fridrich, J.: Minimizing additive distortion in steganography using syndrome-trellis codes. Trans. Inf. For. Secur. 6(3), 920–935 (2011)CrossRefGoogle Scholar
  4. 4.
    Fridrich, J., Kodovsky, J.: Rich models for steganalysis of digital images. Trans. Inf. For. Secur. 7(3), 868–882 (2012)CrossRefGoogle Scholar
  5. 5.
    Fridrich, J., Kodovský, J., Holub, V., Goljan, M.: Steganalysis of content-adaptive steganography in spatial domain. In: Proceedings of the 13th International Conference on Information Hiding, IH’11, pp. 102–117. Springer, Berlin (2011)Google Scholar
  6. 6.
    Holub, V., Fridrich, J.: Low-complexity features for JPEG steganalysis using undecimated DCT. Trans. Inf. For. Secur. 10(2), 219–228 (2015a)CrossRefGoogle Scholar
  7. 7.
    Holub, V., Fridrich, J.: Phase-aware projection model for steganalysis of JPEG images. In: Proceedings on SPIE 9409:94, 090T–94, 090T-11 (2015b)Google Scholar
  8. 8.
    Holub, V., Fridrich, J., Denemark, T.: Random projections of residuals as an alternative to co-occurrences in steganalysis. In: Proceedings on SPIE 8665:86, 650L–86, 650L-11 (2013)Google Scholar
  9. 9.
    Holub, V., Fridrich, J., Denemark, T.: Universal distortion function for steganography in an arbitrary domain. EURASIP J. Inf. Secur. 1, 1–13 (2014)Google Scholar
  10. 10.
    Ker, A.D.: Implementing the projected spatial rich features on a GPU. In: Proceedings on SPIE 9028:90, 280K–90, 280K-10 (2014)Google Scholar
  11. 11.
    Khayam, S.A.: The discrete cosine transform (DCT): theory and application. Texts Comput. Sci. 41(1), 135–147 (2003)Google Scholar
  12. 12.
    Kodovský, J., Fridrich, J.: Steganalysis of JPEG images using rich models. In: Proceedings on SPIE 8303:83, 030A–83, 030A–13 (2012)Google Scholar
  13. 13.
    Kodovský, J., Pevný, T., Fridrich, J.: Modern steganalysis can detect YASS. In: Proceedings on SPIE 7541:754, 102–754, 102-11 (2010)Google Scholar
  14. 14.
    Kodovský, J., Fridrich, J., Holub, V.: Ensemble classifiers for steganalysis of digital media. Trans. Inf. For. Secur. 7(2), 432–444 (2012)CrossRefGoogle Scholar
  15. 15.
    Liu, Q.: Steganalysis of DCT-embedding based adaptive steganography and YASS. In: Proceedings of the Thirteenth ACM Multimedia Workshop on Multimedia and Security, MMSec ’11, pp. 77–86. ACM, New York (2011)Google Scholar
  16. 16.
    Michel, P., Chestnutt, J., Kagami, S., Nishiwaki, K., Kuffner, J., Kanade, T.: GPU-accelerated real-time 3D tracking for humanoid locomotion and stair climbing. In: International Conference on Intelligent Robots and Systems, 2007, IROS 2007, IEEE/RSJ, pp. 463–469 (2007)Google Scholar
  17. 17.
  18. 18.
    Obukhov, A., Kharlamov, A.: Discrete cosine transform for 8x8 blocks with CUDA. Nvidia White Paper (2008).
  19. 19.
    Pevný, T., Fridrich, J.: Merging Markov and DCT features for multi-class JPEG steganalysis. In: Proceedings on SPIE 6505:650, 503–650, 503-13 (2007)Google Scholar
  20. 20.
    Pevný, T., Bas, P., Fridrich, J.: Steganalysis by subtractive pixel adjacency matrix. Trans. Inf. For. Secur. 5(2), 215–224 (2010a)CrossRefGoogle Scholar
  21. 21.
    Pevný, T., Filler, T., Bas, P.: Using high-dimensional image models to perform highly undetectable steganography. In: Proceedings of the 12th International Conference on Information Hiding, IH’10, pp. 161–177. Springer, Berlin (2010b)Google Scholar
  22. 22.
    Podlozhnyuk, V.: Image convolution with CUDA. Nvidia Corporation White Paper (2007).
  23. 23.
    Shi, Y.Q., Sutthiwan, P., Chen, L.: Textural features for steganalysis. In: Proceedings of the 14th International Conference on Information Hiding, IH’12, pp. 63–77. Springer, Berlin (2013)Google Scholar
  24. 24.
    Smith, S.W.: The Scientist and Engineer’s Guide to Digital Signal Processing. California Technical Publishing, San Diego (1997)Google Scholar
  25. 25.
    Song, X., Liu, F., Yang, C., Luo, X., Zhang, Y.: Steganalysis of adaptive JPEG steganography using 2D Gabor filters. In: Proceedings of the 3rd ACM Workshop on Information Hiding and Multimedia Security, IHMMSec ’15, pp. 15–23. ACM, New York (2015)Google Scholar
  26. 26.
    Tang, W., Li, H., Luo, W., Huang, J.: Adaptive steganalysis against wow embedding algorithm. In: Proceedings of the 2nd ACM Workshop on Information Hiding and Multimedia Security, IHMMSec’14, pp. 91–96. ACM, New York (2014)Google Scholar
  27. 27.
    Vogelgesang, M., Chilingaryan, S., Rolo, T.d., Kopmann, A.: UFO: A scalable GPU-based image processing framework for on-line monitoring. In: Proceedings of the 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems, HPCC ’12, pp. 824–829. IEEE Computer Society, Washington (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • Chao Xia
    • 1
    Email author
  • Qingxiao Guan
    • 1
  • Xianfeng Zhao
    • 1
  • Chengduo Zhao
    • 1
  1. 1.State Key Laboratory of Information Security, Institute of Information EngineeringChinese Academy of SciencesBeijingChina

Personalised recommendations