Generation a shared secret using artificial neural networks
https://doi.org/10.21122/2309-4923-2019-2-49-56
Abstract
In the Kanter’s and Kinsella’s works is proposes the use of two synchronized artificial neural networks (SANN) connected by opening communication channel to confidential formation of a common cryptographic key. At the same time, there are few questions of practical suitability of this technology for cryptographic applications. There are no recommendations on the choice of parameters of the used networks, ensuring acceptable speed and guaranteed confidentiality of the generated general secret.
In this regard, it is interesting to substantiate the rational values of the parameters of ANN from the point of view of cryptographic requirements and security analysis of the proposed method of formation of cryptographic keys.
About the Authors
U. F. HolikauBelarus
M. L. Radziukevich
Belarus
References
1. Kanter, I. The Theory of Neural Networks and Cryptography, Quantum Computers and Computing / I. Kanter, W. Kinzel. 2005. Vol. 5, n. 1. – P. 130140.
2. Kinzel, W. Neural Cryptography / W. Kinzel, / I. Kanter // 9th International Conference on Neural Information Processing, Singapore, 2002.
3. Ruttor, A. Dynamics of neural cryptography / A. Ruttor, I. Kanter, and W. Kinzel // Phys. Rev. E, 75(5):056104, 2007.
4. Golikov V. F., Brich N. V., Pivovarov V. L. «On some problems in the distribution of cryptographic keys using artificial neural networks», System Analysis and Applied Informatics, № 1–3, 2014.
5. Plonkovski, M. Cryptographic transformation of information based on neural network technology / M. Plonkovski, P. P. Urbanovich // Proceedings of BSTU. Series VI. Physics and Mathematics and Informatics; by ed. I. M. Zharsky. – Minsk: BSTU, 2005.
Review
For citations:
Holikau U.F., Radziukevich M.L. Generation a shared secret using artificial neural networks. «System analysis and applied information science». 2019;(2):49-56. (In Russ.) https://doi.org/10.21122/2309-4923-2019-2-49-56