Enhancing the secrecy of a cryptographic key generated using synchronized artificial neural networks1
https://doi.org/10.37661/1816-0301-2020-17-1-102-108
Abstract
The main options for the formation of a shared secret using synchronized artificial neural networks and possible patterns of behavior of a cryptanalyst are considered. To solve the problem of increasing the confidentiality of the generated shared secret, if it is used as a cryptographic key, it is proposed to use the mixing a certain number of results of individual synchronizations (convolution). As a mixing function, we consider the convolution of the vectors of network weights by bitwise addition modulo 2 of all the results of individual synchronizations. It is shown that the probability of success of a cryptanalyst is reduced exponentially with an increase of the number of terms in the convolution and can be chosen arbitrarily small. Moreover, the distribution law of the generated key after convolution is close to uniform and the uniformity increases with the number of terms in the convolution.
About the Authors
M. L. Radziukevich
Scientific Production-Republican Unitary Enterprise "Research Institute for the Technical Protection of Information"
Belarus
Maryna L. Radziukevich, Master Sci. (Eng.), Head of the Testing Laboratory for Information Security Requirements, Winner of the competition of young scientists at the XXIV scientific-practical conference "Comprehensive information protection."
Belarus
Maryna L. Radziukevich, Master Sci. (Eng.), Head of the Testing Laboratory for Information Security Requirements, Winner of the competition of young scientists at the XXIV scientific-practical conference "Comprehensive information protection."
V. F. Golikov
Belarusian National Technical University
Belarus
Vladimir F. Golikov, Dr. Sci. (Eng.), Professor of the Department of Information Technologies in Management
Belarus
Vladimir F. Golikov, Dr. Sci. (Eng.), Professor of the Department of Information Technologies in Management
References
1. Kanter I., Kinzel W. The Theory of Neural Networks and Cryptography, Quantum Computers and Computing, 2005, vol. 5, nо. 1, рр. 130−140.
2. Kinzel W., Kanter I. Neural cryptography. 9th International Conference on Neural Information Processing, Singapore, 2002. Singapore, 2002, vol. 3, рр. 1351–1354.
3. Ruttor A., Kanter I., Kinzel W. Dynamics of neural cryptography. Physical Review E, 2007, vol. 75, iss. 5, рр. 1–9.
4. Plonkovski M., Urbanovich P. P., Zharsky I. M. (ed.). Kriptograficheskoye preobrazovaniye informatsii na osnove neyrosetevykh tekhnologii [Cryptographic transformation of information based on neural network technology]. Trudy Belorusskogo gosudarstvennogo tehnologicheskogo universiteta. Ser. VI. Fizikomatematicheskiye nauki i informatika [Proceedings of the Belarusian State Technical University. Ser. VI. Physics and Mathematics and Computer Science]. Minsk, Belarusian State Technical University, 2005, рр. 161–164 (in Russian).
5. Golikov V. F., Brich N. V., Pivovarov V. L. O nekotorykh problemakh v zadachakh raspredeleniya kriptograficheskikh klyuchey s pomoshch'yu iskusstvennykh neyronnykh setey [About some problems in the distribution of cryptographic keys using artificial neural networks]. Sistemnyy analiz i prikladnaya informatika [System Analysis and Applied Informatics], 2014, no. 1–3, рр. 42–46 (in Russian).
6. Golikov V. F., Ksenevich A. Yu. Ataka na sinkhroniziruyemyye iskusstvennyye neyronnyye seti, formiruyushchiye obshchiy sekret, metodom otlozhennogo perebora [Attack on synchronized artificial neural networks, forming a common secret, by delayed brute force method]. Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radiojelektroniki [Reports of the Belarusian State University of Informatics and Radioelectronics], 2017, no. 8, рр. 48–53 (in Russian).
7. Golikov V. F., Radziukevich M. L. Formirovaniye obshchego sekreta s pomoshch'yu iskusstvennykh neyronnykh setey [The formation of a common secret using artificial neural networks]. Sistemnyy analiz i prikladnaya informatika [System Analysis and Applied Informatics], 2019, no. 2, рр. 49–56 (in Russian).
8. Bennett C. H., Brassard G., Crepeau C., Maurer U. M. Generalized privacy amplification. IEEE Transaction on Information Theory, 1995, vol. 41, nо. 6, рр. 1915–1923.
9. Boumeyster D., Ekert A., Tsaylinger A. Fizika kvantovoy informatsii. Physics of Quantum Information. Moscow, Postmarket, 2002, 276 p. (in Russian).
10. Kilin S. Ya., Khoroshko D. B., Nizovtsev A. P. Kvantovaya kriptografiya: idei i praktika. Quantum cryptography: Ideas and Practice. Minsk, Belaruskaya navuka, 2007, 391 p. (in Russian).
Review
For citations:
Radziukevich M.L., Golikov V.F. Enhancing the secrecy of a cryptographic key generated using synchronized artificial neural networks1. Informatics. 2020;17(1):102-108. (In Russ.) https://doi.org/10.37661/1816-0301-2020-17-1-102-108
Views: 811
Email this article 