Artificial neural networks as a mechanism for obfuscation of computations | Applied Discrete Mathematics. Supplement. 2019. № 12. DOI: 10.17223/2226308X/12/46

Artificial neural networks as a mechanism for obfuscation of computations

The subject of the paper is the possibility of using artificial neural networks as a mechanism for strongly obfuscating computations. The problem of the obfuscation and the main ideas and methods for solving this problem are discussed. The concept of a neural network obfuscator is introduced and its properties are proved. The advantages and disadvantages of the proposed approach are discussed.

Download file

Counter downloads: 140

Keywords

искусственная нейронная сеть, обфускация, artificial neural network, obfuscation

Authors

Name	Organization	E-mail
Eliseev V. L.	Center for Scientific Research and Advanced Development of OJSC InfoTeKS; National Research University "Moscow Energy Institute"	vlad-eliseev@mail.ru

Всего: 1

References

Venkatesh S. and Ertaul L. Novel obfuscation algorithms for software security // Proc. Intern. Conf. SERP'05. 2005. V. 1. P. 209-215.

Варновский Н. П., Захаров В. А., Кузюрин Н. Н. Математические проблемы обфускации // Математика и безопасность информационных технологий. Материалы конф. в МГУ 28-29 октября 2004г. М.: МЦНМО, 2005. С. 65-91.

Barak B., Goldreich O., Impagliazzo R., et al. On the (im)possibility of obfuscating programs // Crypto'01. LNCS. 2001. V.2139. P. 1-18.

Goldwasser S. and Guy N. R. On best-possible obfuscation // J. Cryptology. 2007. No. 27. P. 480-505.

Garg S., Gentry C., Halevi S., et al. Candidate indistinguishability obfuscation and functional encryption for all circuits // Proc. 54th IEEE Ann. Symp. FOCS'13. October 26-29, 2013. P. 40-49.

Albrecht M. R., Cocis C., Laguillaumie F. and Langlois A. Implementing candidate graded encoding schemes from ideal lattices // ASIACRYPT 2015. LNCS. 2015. V. 9453. P. 752-775.

Ma H., Ma X., Liu W., et al. Control flow obfuscation using neural network to fight concolic testing // 10th Intern. ICST Conf., SecureComm 2014, Beijing, China, September 24-26, 2014. Part I. P. 287-304.

Yan Wang Obfuscation with Turing Machine. A Thesis in Information Sciences and Technology. Pennsylvania State University, 2017. 42 p.

Хайкин С. Нейронные сети: полный курс. 2-е изд. М.: Вильямс, 2008.

Алексеев Д. В. Приближение функций нескольких переменных нейронными сетями // Фундаментальная и прикладная математика. 2009. Т. 15б. №3. С. 9-21.

Hecht-Nielsen R. Kolmogorov's mapping neural network existence theorem // IEEE First Ann. Int. Conf. Neural Networks. San Diego, 1987. V.3. P. 11-13.