Algorithmic Learning for Steganography: Proper Learning of k-term DNF Formulas from Positive Samples

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9472)


Proper learning from positive samples is a basic ingredient for designing secure steganographic systems for unknown covertext channels. In addition, security requirements imply that the hypothesis should not contain false positives. We present such a learner for k-term DNF formulas for the uniform distribution and a generalization to q-bounded distributions. We briefly also describe how these results can be used to design a secure stegosystem.


Proper Learning Secure Stegosystem Candidate Monomers Steganalyst Sampling Oracle 
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.


  1. 1.
    Alekhnovich, M., Braverman, M., Feldman, V., Klivans, A.R., Pitassi, T.: The complexity of properly learning simple concept classes. J. Comput. Syst. Sci. 74(1), 16–34 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.K.: Learnability and the Vapnik-Chervonenkis dimension. J. ACM 36(4), 929–965 (1989)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    De, A., Diakonikolas, I., Servedio, R.A.: Learning from satisfying assignments. In: Indyk, P. (ed.) Proc. SODA, pp. 478–497. SIAM, Philadelphia (2015)Google Scholar
  4. 4.
    Dedić, N., Itkis, G., Reyzin, L., Russell, S.: Upper and lower bounds on black-box steganography. J. Cryptology 22(3), 365–394 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Flammini, M., Marchetti-Spaccamela, A., Kučera, L.: Learning DNF formulae under classes of probability distributions. In: Proc. COLT, pp. 85–92. ACM, New York (1992)Google Scholar
  6. 6.
    Fridrich, J.: Steganography in digital media: principles, algorithms, and applications. Cambridge University Press, New York (2009)CrossRefzbMATHGoogle Scholar
  7. 7.
    Hopper, N., von Ahn, L., Langford, J.: Provably secure steganography. IEEE T. Comput. 58(5), 662–676 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Jerrum, M.R., Valiant, L.G., Vazirani, V.V.: Random generation of combinatorial structures from a uniform distribution. Theor. Comput. Sc. 43, 169–188 (1986)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Ker, A.D., Bas, P., Böhme, R., Cogranne, R., Craver, S., Filler, T., Fridrich, J., Pevný, T.: Moving steganography and steganalysis from the laboratory into the real world. In: Proc. IH&MMSec, pp. 45–58. ACM, New York (2013)Google Scholar
  10. 10.
    Kodovsky, J., Fridrich, J., Holub, V.: Ensemble classifiers for steganalysis of digital media. IEEE T. Inform. Forensics and Sec. 7(2), 432–444 (2012)CrossRefGoogle Scholar
  11. 11.
    Kucera, L., Marchetti-Spaccamela, A., Protasi, M.: On learning monotone DNF formulae under uniform distributions. Inform. Comput. 110(1), 84–95 (1994)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Liśkiewicz, M., Reischuk, R., Wölfel, U.: Grey-box steganography. Theor. Comput. Sc. 505, 27–41 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Natarajan, B.K.: Probably approximate learning of sets and functions. SIAM J. Comput. 20(2), 328–351 (1991)MathSciNetCrossRefzbMATHGoogle Scholar
  14. 14.
    Pitt, L., Valiant, L.G.: Computational limitations on learning from examples. J. ACM 35(4), 965–984 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Sakai, Y., Maruoka, A.: Learning monotone log-term DNF formulas under the uniform distribution. Theory of Comput. Syst. 33(1), 17–33 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Sakai, Y., Maruoka, A.: Learning \(k\)-term monotone boolean formulae. In: Doshita, S., Furukawa, K., Jantke, K.P., Nishida, T. (eds.) ALT 1992. LNCS, vol. 743, pp. 195–207. Springer, Heidelberg (1993)CrossRefGoogle Scholar
  17. 17.
    Schaathun, H.G.: Machine Learning in Image Steganalysis. Wiley-IEEE Press, Chichester (2012)CrossRefGoogle Scholar
  18. 18.
    Valiant, L.G.: A theory of the learnable. CACM 27(11), 1134–1142 (1984)CrossRefzbMATHGoogle Scholar
  19. 19.
    Verbeurgt, K.: Learning DNF under the uniform distribution in quasi-polynomial time. In: Proc. COLT, pp. 314–326. Morgan Kaufmann Publishers Inc., San Francisco (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  1. 1.Institut für Theoretische InformatikUniversität zu LübeckLübeckGermany
  2. 2.Graduate School for Computing in Medicine and Life SciencesUniversität zu LübeckLübeckGermany

Personalised recommendations