Geodesic
On the security of a neural network-based biometric authentication scheme
Matematičeskie voprosy kriptografii, Tome 5 (2014) no. 2, pp. 87-98 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

We show that neuron weights used in neural network-based biometric authentication scheme defined in GOST R 52633 standard series contain all the information on biometric data and secret key of the legitimate user. So, the complexity of evaluating (with known tables of neuron weights) the legitimate user's secret key is equivalent to the complexity of evaluating one solution of a corresponding system of linear inequalities. Thus, first, neuron weights should be considered as a part of a secret key of the authentication system, and, second, several methods for neural networks protection proposed in the standard are inefficient. 
@article{MVK_2014_5_2_a9,
     author = {G. B. Marshalko},
     title = {On the security of a~neural network-based biometric authentication scheme},
     journal = {Matemati\v{c}eskie voprosy kriptografii},
     pages = {87--98},
     year = {2014},
     volume = {5},
     number = {2},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/MVK_2014_5_2_a9/}
}
TY  - JOUR
AU  - G. B. Marshalko
TI  - On the security of a neural network-based biometric authentication scheme
JO  - Matematičeskie voprosy kriptografii
PY  - 2014
SP  - 87
EP  - 98
VL  - 5
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/MVK_2014_5_2_a9/
LA  - en
ID  - MVK_2014_5_2_a9
ER  - 
%0 Journal Article
%A G. B. Marshalko
%T On the security of a neural network-based biometric authentication scheme
%J Matematičeskie voprosy kriptografii
%D 2014
%P 87-98
%V 5
%N 2
%U http://geodesic.mathdoc.fr/item/MVK_2014_5_2_a9/
%G en
%F MVK_2014_5_2_a9
G. B. Marshalko. On the security of a neural network-based biometric authentication scheme. Matematičeskie voprosy kriptografii, Tome 5 (2014) no. 2, pp. 87-98. http://geodesic.mathdoc.fr/item/MVK_2014_5_2_a9/

[1] Information protection. Information protection technology. Requirements to the means of high-reliability biometric authentication, GOST R 52633.0-2006

[2] Information protection. Information protection technology. The neural net biometry-code convertor automatic training, GOST R 52633.5-2011

[3] Efimov O. V., Funtikov V. A., Jazov U. K., “The neuronet converter “biometry-code” structure and interconnections choice strategy”, Neurocomputers: development, application, 6 (2009), 14–16

[4] Kuznetsov V. V., Ushmaev O. V., “Algorithms for protected biometric verification based on the binary representation of fingerprint topology”, Informatics and its applications, 6:1 (2012), 132–140 (in Russian)

[5] Majorov A. V., “Biometric hash-function”, Proc. TPCYR-2009, JSC PNIEI, 2009 (in Russian)

[6] Nazarov I. G., Efimov O. V., Yazov Y. K., “The package of national standards, ensuring biometric and neural network protection of mass circulated personal data privacy”, Neurocomputers: development, application, 3 (2012), 9–16

[7] Zolotykh N. Yu., Deciphering of threshold and close to threshold $q$-ary logic functions, Ph. D. Thesis, NNGU, 1998 (in Russian)

[8] Zorkal'tsev V. I., Filatov A. Yu., “New variants of dual interior point algorithms for systems of linear inequalities”, Zh. Vychisl. Mat. Mat. Fiz., 44:7 (2004), 1234–1243 | MR | Zbl

[9] Ushmaev O. S., “Protected biometric authentication”, CSE Days. Theory 2011, Ekaterinburg, 2011 (in Russian)

[10] Haykin S., Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice-Hall, 1999

[11] Chernikova V., “Algorithm for finding a general formula for the non-negative solutions of a system of linear inequalities”, Zh. Vychisl. Mat. Mat. Fiz., 5:2 (1965), 334–337 | MR | Zbl

[12] Jazov U. K., Nazarov I. G., Ivanov A. I., Yefimov O. V., “Neuronet technology for protection of personal data”, Neurocomputers: development, application, 6 (2009), 5–10

[13] Dodis Y., Reyzin L., Smith A., “Fuzzy extractors: How to generate strong keys from biometrics and other noisy data”, Proc. EUROCRYPT' 04, LNCS, 3072, 2004, 523–540 | MR

[14] Boyen X., “Reusable cryptographic fuzzy extractors”, Proc. 11th ACM Conference on Computer and Communication Security, 2004