Optimization of Artificial Neural Network Structure in the Case of Steganalysis

  • Zuzana Oplatkova
  • Jiri Holoska
  • Michal Prochazka
  • Roman Senkerik
  • Roman Jasek
Part of the Intelligent Systems Reference Library book series (ISRL, volume 38)


This research introduces a method of steganalysis by means of neural networks and its structure optimization. The main aim is to explain the approach of revealing a hidden content in jpeg files by feed forward neural network with Levenberg-Marquardt training algorithm. This work is also concerned to description of data mining techniques for structure optimization of used neural network. The results showed almost 100% success of detection.


Artificial Neural Network Hide Layer Discrete Cosine Transform Hide Neuron Cover Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cole, E., Krutz, D.R.: Hiding Sight, 321 p. Wiley Publishing, Inc., United States of America (2003) ISBN 0-471-44449-9Google Scholar
  2. 2.
    Goldwasser, S., Bellare, M.: Lecture Notes on Cryptography, 283 p. MIT, Cambridge (2001),
  3. 3.
    Hertz, J., Kogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Addison–Wesley (1991)Google Scholar
  4. 4.
  5. 5.
  6. 6.
  7. 7.
  8. 8.
    Provos, N., Honeyman, P.: Detecting Steganographic Content on the Internet. CITI Technical Report 01-11 (2001)Google Scholar
  9. 9.
    Provos, N., Honeyman, P.: Hide and Seek: An Introduction to Steganography. IEEE Security & Privacy 1(3), 32–44 (2003)CrossRefGoogle Scholar
  10. 10.
    Westfeld, A., Pfitzmann, A.: Attacks on Steganographic Systems. In: Proceedings of Information Hiding - Third International Workshop. Springer (September 1999)Google Scholar
  11. 11.
    Fridrich, J., Goljan, M., Hogea, D.: Steganalysis of JPEG images: Breaking the F5 algorithm. In: Petitcolas, F.A.P. (ed.) IH 2002. LNCS, vol. 2578, pp. 310–323. Springer, Heidelberg (2003), (last accessed: December 24, 2003)CrossRefGoogle Scholar
  12. 12.
    Fridrich, J., Goljan, M., Hogea, D.: New Methodology for Breaking Steganographic Techniques for JPEGs. Submitted to SPIE: Electronic Imaging 2003, Security and Watermarking of Multimedia Contents, Santa Clara, California (2003)Google Scholar
  13. 13.
    Fridrich, J.: Feature-Based Steganalysis for JPEG Images and Its Implications for Future Design of Steganographic Schemes. In: Fridrich, J. (ed.) IH 2004. LNCS, vol. 3200, pp. 67–81. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Farid, H., Lyu, S.: Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines. In: Petitcolas, F.A.P. (ed.) IH 2002. LNCS, vol. 2578, pp. 340–354. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  15. 15.
    Hempstalk, K.: Hiding Behind Corners: Using Edges in Images for Better Steganography. In: Proceedings of the Computing Women’s Congress, Hamilton, New Zealand, February 11-19 (2006)Google Scholar
  16. 16.
  17. 17.
    Gül, G., Dirik, A.E., Avcibas, I.: Steganalytic Features for JPEG Compression-Based Perturbed Quantization. IEEE Signal Processing Letters 3 (March 2007)Google Scholar
  18. 18.
    Matousek, R.: Using AI Methods to Find a Non-Linear Regression Model with a Coupling Condition. Engineering Mechanics 17(5/6), 419–431 (2011) ISSN: 1802-1484 Google Scholar
  19. 19.
    Volna, E.: Learning and evolution in artificial neural networks: Comparison study. In: ANNIP 2008, Madeira, Portugal, pp. 10–17 (2008) ISBN: 978-989-8111-33-3 Google Scholar
  20. 20.
    Volna, E.: Design of neural network trees. In: Mendel 2008, pp. 978–980. Technical University of Brno (2008) ISBN: 978-80-214-3675-6Google Scholar
  21. 21.
    Zelinka, I.: SOMA – Self Organizing Migrating Algorithm. In: Babu, B.V., Onwubolu, G. (eds.) New Optimization Techniques in Engineering, 33, ch. 7. Springer (2004)Google Scholar
  22. 22.
    Price, K.: An Introduction to Differential Evolution. In: Corne, D., Dorigo, M., Glover, F. (eds.) New Ideas in Optimization, pp. 79–108. McGraw-Hill, LondonGoogle Scholar
  23. 23.
    Matousek, R.: HC12: The Principle of CUDA Implementation. In: MENDEL 2010. Mendel Journal series, pp. 303–308. VUT, Brno (2010) ISBN: 978-80-214-4120-0, ISSN: 1803-3814Google Scholar
  24. 24.
    Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 2nd edn., pp. 385–392. MIT Press and McGraw-Hill, Cambridge (2001) ISBN 0-262-03293-7. Section 16.3Google Scholar
  25. 25.
  26. 26.
    Obayashi, S., Jeong, S., Chiba, K.: Multiobjective Design Exploration for Aerodynamic Configurations. American Institute of Aeronautics and Astronautics (August 22, 2007)Google Scholar
  27. 27.
    Mosavi, A.: Multiple Criteria Decision-Making Preprocessing Using Data Mining Tools. IJCSI International Journal of Computer Science Issues 7(2(1)) (March 2010) ISSN (Online): 1694-0784Google Scholar
  28. 28.
    Witten, I.H., Frank, E., Hall, M.A.: Datamining – Practical Machine Learning Tools and Techniques. Morgan Kaufmann (2011) ISBN: 978-0-12-374856-0Google Scholar
  29. 29.
    Software OutGuess,
  30. 30.
    Defending Against Statistical Steganalysis Niels Provos. In: 10th USENIX Security Symposium, Washington, DC (August 2001)Google Scholar
  31. 31.
    Hetzl S.: Steghide (1) - Linux man page, (cit. May 21, 2008)
  32. 32.
    Westfeld, A.: High Capacity Despite Better Steganalysis (F5-—A Steganographic Algorithm). In: Moskowitz, I.S. (ed.) IH 2001. LNCS, vol. 2137, pp. 289–302. Springer, Heidelberg (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Zuzana Oplatkova
    • 1
  • Jiri Holoska
    • 1
  • Michal Prochazka
    • 1
  • Roman Senkerik
    • 1
  • Roman Jasek
    • 1
  1. 1.Faculty of Applied InformaticsTomas Bata University in ZlínZlínCzech Republic

Personalised recommendations