Distance of the initial weights of tree parity machine drawn from different distributions

• Autorzy: Dolecki M. , Kozera R.

Identyfikatory

DOI

10.12913/22998624/2380

• Języki publikacji: EN

Abstrakty

EN

It is well-known that artificial neural networks have the ability to learn based on the provisions of new data. A special case of the so-called supervised learning is a mutual learning of two neural networks. This type of learning applied to a specific networks called Tree Parity Machines (abbreviated as TPM networks) leads to achieving consistent weight vectors in both of them. Such phenomenon is called a network synchronization and can be exploited while constructing cryptographic key exchange protocol. At the beginning of the learning process both networks have initialized weights values as random. The time needed to synchronize both networks depends on their initial weights values and the input vectors which are also randomly generated at each step of learning. In this paper the relationship between the distribution, from which the initial weights of the network are drawn, and their compatibility is discussed. In order to measure the initial compatibility of the weights, the modified Euclidean metric is invoked here. Such a tool permits to determine the compatibility of the network weights’ scaling in regard to the size of the network. The proper understanding of the latter permits in turn to compare TPM networks of various sizes. This paper contains the results of the simulation and their discussion in the context of the above mentioned issue.

Słowa kluczowe

EN

neural networks; neurocryptography

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2015
• Tom: Vol. 9, nr 26
• Strony: 137–--142
• Opis fizyczny: Bibliogr. 18 poz., fig., tab.

Twórcy

autor

Dolecki M.

• The John Paul II Catholic University of Lublin, Konstantynów 1H, 20-708 Lublin, Poland

autor

Kozera R.

• Warsaw University of Life Sciences – SGGW, Nowoursynowska 159, 02-776 Warsaw, Poland

Bibliografia

• 1. Barker E., Barker W., Burr W., Polk W., Smid M.: Recommendation for key management – part 1: general (revision 3). National Institute of Standards and Technology Special Publication, 2012, 800–857.
• 2. Bisalapur S.: Design of an efficient neural key distribution center. International Journal of Artificial Intelligence & Applications, 2 (1), 2011, 60–69.
• 3. Dolecki M., Kozera R.: Threshold method of detecting long-time TPM synchronization. Proceedings of the 12th International Conference on Computer Information Systems and Industrial Management Applications, Lecture Notes in Computer Science 8104, Springer – Verlag Berlin, 2013, 241-252.
• 4. Dolecki M., Kozera R., Lenik K.: The evaluation of the TPM synchronization on the basis of their outputs. Journal of Achievements in Materials and Manufacturing Engineering, 57, 2013, 91–98.
• 5. Dolecki M., Kozera R.: Distribution of the Tree Parity Machine synchronization time. Advances in Science and Technology Research Journal, 18, 2013, 20–27.
• 6. Gil A., Karoń T.: Analiza środków i metod ochrony systemów operacyjnych. Postępy Nauki i Techniki, 12, 2012, 149–168.
• 7. Hassoun M.: Fundamentals of Artificial Neural Networks. MIT Press, 1995.
• 8. Ibrachim S., Maarof M.: A review on biological inspired computation in cryptology. Jurnal Teknologi Maklumat, 17(1), 2005, 90–98.
• 9. Kanter I., Kinzel W.: The theory of neural networks and cryptography. The Physics of Communication: Proceedings of the XXII Solvay Conference on Physics, 2002, 631–644.
• 10. Kanter I., Kinzel W., Kanter E.: Secure exchange of information by synchronization of neural networks. Europhysics Letters, 57, 2002, 141–147.
• 11. Klein E., Mislovaty R., Kanter I., Ruttor A., Kinzel W.: Synchronization of neural networks by mutual learning and its application to cryptography. Advances in Neural Information Processing Systems, 17, MIT Press, Cambridge, 2005, 689–696.
• 12. Klimov A., Mityagin A., Shamir A.: Analysis of neural cryptography, [In:] Y. Zheng (ed.), Advances in Cryptology – ASIACRYPT 2002, Springer, 2003, 288–289.
• 13. McCulloch W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 1943, 115–133.
• 14. Menezes A., Vanstone S., Van Oorschot P.: Handbook of Applied Cryptography. CRC Press, 1996.
• 15. Ruttor A.: Neural Synchronization and Cryptography. PhD thesis, Wurzburg 2006.
• 16. Ruttor A., Kinzel W., Naeh R., Kanter I.: Genetic attack on neural cryptography. Physical Review E, 73(3), 2006, 036121.
• 17. Stokłosa J., Bilski T., Pankowski T.: Bezpieczeństwo danych w systemach informatycznych. PWN, 2001.
• 18. Volkmer M., Wallner S.: Tree parity machine re-keying architectures. IEEE Transactions on Computers, 54, 2005, 421–427.