Neural Network as a Programmable Block Cipher

  • Piotr Kotlarz
  • Zbigniew Kotulski


A model of Boolean neural network is proposed as a substitute of a bock cipher. Such a network has functionality of the block cipher and one additional advantage: it can change its cryptographic properties without reprogramming, by training the network with a new training set. The constriction of the network is presented with an analysis of the applied binary transformations. Also three methods of training the network (what corresponds to the re-keying of a block cipher) are presented. Their security and effectiveness are analyzed and compared.


Neural Network Encryption Algorithm Block Cipher Server Side Client Side 
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]
    E. Mosanya, Ch. Teuscher, H.F. Restrepo, P. Galley, E. Sanchez, CryptoBooster: A Reconfigurable and Modular Cryptographic Coprocessor, in: Cryptographic Hardware and Embedded Systems: Proc. CHES’99, LNCS 1717, Springer Berlin 1999.Google Scholar
  2. [2]
    R. Taylor, S. Goldstein, A High-Performance Flexible Architecture for Cryptography, Proceedings of the Workshop on Cryptographic Hardware and Embedded Systems, Worcester August 1999.Google Scholar
  3. [3]
    C.H. Lim, CRYPTON: A New 128-bit Block Cipher, Proceedings of the First Advanced Encryption Standard Candidate Conference, Ventura, California, NIST, 1998.Google Scholar
  4. [4]
    L.R. Knudsen, Correlations in RC6, Department of Informatics, University of Bergen, N 5020 Bergen:, July 29, 1999.Google Scholar
  5. [5]
    W. Laskowski, Programmable logical circuits as tools supporting cryptographic data protection, Przeglad Telekomunikacyjny, Vol. LXXIV, no. 3/2001. (In Polish)Google Scholar
  6. [6]
    T. Łuba, K. Jasiński, B. Zwierzchowski, Programmable logical circuits processing signals and information – digital circuit engineering in multimedia and cryptography, Przeglad Telekomunikacyjny Vol. LXXVI no. 8–9/2003. (In Polish)Google Scholar
  7. [7]
    P. Kotlarz, Z. Kotulski, Application of neural networks for implementation of cryptographic functions, in:Multimedia in Business and Education, ISBN83-9182218-7-0Google Scholar
  8. [8]
    P.Kotlarz, Z.Kotulski, On application of neural networks for S-boxes design, in: P. S. Szczepaniak, J.Kacprzyk, A. Niewiadomski, ed. Advances in Web Intelligence, AWIC 2005, LNCS 3528, pp. 243-248, Springer, Berlin 2005.Google Scholar
  9. [9]
    P. Kotlarz, Z. Kotulski, Artificial intelligence methods in the present-day cryptography, Proceedings of Ploug’05, Zakopane 2005. (In Polish)Google Scholar
  10. [10]
    I. Kanter, W. Kinzel, E. Kanter, Secure exchange of information by synchronization of neural networks, Europhys. Lett. 57, 141, 2002.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Piotr Kotlarz
    • 1
  • Zbigniew Kotulski
    • 2
  1. 1.Kazimierz Wielki UniversityChodkiewicza 30
  2. 2.Institute of Fundamental Technological Research, PAS and Institute of TelecommunicationsWUT

Personalised recommendations