Compression-Based Integral Prior Classification for Improving Steganalysis

  • Viktor Monarev
  • Ilja Duplischev
  • Andrey PestunovEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9977)


We propose the integral prior classification approach for binary steganalysis which imply that several detectors are trained, and each detector is intended for processing only images with certain compression rate. In particular, the training set is splitted into several parts according to the images compression rate, then a corresponding number of detectors are trained, but each detector uses only an ascribed to it subset. The testing images are distributed between the detectors also according to their compression rate. We utilize BOSSbase 1.01 as benchmark data along with HUGO, WOW and S-UNIWARD as benchmark embedding algorithms. Comparison with state-of-the-art results demonstrated that, depending on the case, the integral prior classification allows to decrease the detection error by 0.05–0.16.


Information hiding Steganalysis Support vector machine Compression HUGO UNIWARD WOW Prior classification SRM PSRM 


  1. 1.
    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). doi: 10.1007/978-3-642-24178-9_5 CrossRefGoogle Scholar
  2. 2.
    Boncelet, C., Marvel, L., Raqlin, A.: Compression-based steganalysis of LSB embedded images. In: Proceedings of SPIE, Security, Steganography, and Watermarking of Multimedia Contents VIII, vol. 6072, pp. 75-84 (2006)Google Scholar
  3. 3.
    Fridrich, J.: Rich models for steganalysis of digital images. IEEE Trans. Inf. Forensics Secur. 7(3), 868–882 (2012)CrossRefGoogle Scholar
  4. 4.
    Holub, V., Fridrich, J.: Designing steganographic distortion using directional filters. In: Proceedings of 4th IEEE International Workshop on Information Forensics and Security, pp. 234–239 (2012)Google Scholar
  5. 5.
    Holub, V., Fridrich, J.: Digital image steganography using universal distortion. In: Proceedings of 1st ACM Workshop, pp. 59–68 (2013)Google Scholar
  6. 6.
    Holub, V., Fridrich, J.: Random projections of residuals for digital image steganalysis. IEEE Trans. Inf. Forensics Secur. 8(12), 1996–2006 (2013)CrossRefGoogle Scholar
  7. 7.
    Kodovsky, J., Fridrich, J., Holub, V.: Ensemble classifiers for steganalysis of digital media. IEEE Trans. Inf. Forensics Secur. 7(2), 434–444 (2011)Google Scholar
  8. 8.
    Monarev, V., Pestunov, A.: A new compression-based method for estimating LSB replacement rate in color and grayscale images. In: Proceedings of IEEE 7th International Conference on Intelligent Informationa Hiding and Multimedia Signal Processing, IIH-MSP, pp. 57–60 (2011)Google Scholar
  9. 9.
    Monarev, V., Pestunov, A.: A known-key scenario for steganalysis and a highly accurate detector within it. In: Proceedings of IEEE 10th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP, pp. 175–178 (2014)Google Scholar
  10. 10.
    Monarev, V., Pestunov, A.: Prior classification of stego containers as a new approach for enhancing steganalyzers accuracy. In: Qing, S., Okamoto, E., Kim, K., Liu, D. (eds.) ICICS 2015. LNCS, vol. 9543, pp. 445–457. Springer, Heidelberg (2016). doi: 10.1007/978-3-319-29814-6_38 CrossRefGoogle Scholar
  11. 11.
    Pevny, T., Bas, P., Fridrich, J.: Steganalysis by subtractive pixel adjacency matrix. IEEE Trans. Inf. Forensics Secur. 5(2), 215–224 (2010)CrossRefGoogle Scholar
  12. 12.
    Pevný, T., Filler, T., Bas, P.: Using high-dimensional image models to perform highly undetectable steganography. In: Böhme, R., Fong, P.W.L., Safavi-Naini, R. (eds.) IH 2010. LNCS, vol. 6387, pp. 161–177. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-16435-4_13 CrossRefGoogle Scholar
  13. 13.
    LZMA SDK (Software Development Kit).
  14. 14.
    Large Text Compression Benchmark.
  15. 15.
    Break Our Watermarking System, 2nd edn.
  16. 16.
    scikit-learn: Machine Learning in Python.

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Viktor Monarev
    • 1
  • Ilja Duplischev
    • 2
  • Andrey Pestunov
    • 3
    Email author
  1. 1.Institute of Computational Technologies SB RASNovosibirskRussia
  2. 2.Novosibirsk State UniversityNovosibirskRussia
  3. 3.Novosibirsk State University of Economics and ManagementNovosibirskRussia

Personalised recommendations