<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">inform</journal-id><journal-title-group><journal-title xml:lang="ru">Информатика</journal-title><trans-title-group xml:lang="en"><trans-title>Informatics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1816-0301</issn><issn pub-type="epub">2617-6963</issn><publisher><publisher-name>UIIP NASB</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.37661/1816-0301-2025-22-3-72-82</article-id><article-id custom-type="elpub" pub-id-type="custom">inform-1365</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ЗАЩИТА ИНФОРМАЦИИ И НАДЕЖНОСТЬ СИСТЕМ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATION PROTECTION AND SYSTEM RELIABILITY</subject></subj-group></article-categories><title-group><article-title>Аппроксимация двоичных функций на основе двухслойной искусственной нейронной сети</article-title><trans-title-group xml:lang="en"><trans-title>Approximation of binary functions based on two-layer artificial neural network</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Латушкин</surname><given-names>К. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Latushkin</surname><given-names>K. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Латушкин Константин Вадимович - младший научный сотрудник</p><p>пр. Независимости, 4, Минск, 220030</p></bio><bio xml:lang="en"><p>Konstantin V. Latushkin - Junior Researcher</p><p>Nezavisimosti av., 4, Minsk, 220030</p></bio><email xlink:type="simple">LatushkinKV@bsu.by</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Харин</surname><given-names>Ю. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Kharin</surname><given-names>Yu. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Харин Юрий Семенович - доктор физико-математических наук, академик НАН Беларуси, профессор</p><p>пр. Независимости, 4, Минск, 220030</p></bio><bio xml:lang="en"><p>Yuriy S. Kharin - D. Sc. (Phys.-Math.), Acad. of the National Academy of Science of Belarus, Prof.</p><p>Nezavisimosti av., 4, Minsk, 220030</p></bio><email xlink:type="simple">Kharin@bsu.by</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>НИИ прикладных проблем математики и информатики Белорусского государственного университета</institution></aff><aff xml:lang="en"><institution>Research Institute of Applied Problems of Mathematics and Informatics of the Belarusian State University</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>10</day><month>10</month><year>2025</year></pub-date><volume>22</volume><issue>3</issue><fpage>72</fpage><lpage>82</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Латушкин К.В., Харин Ю.С., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Латушкин К.В., Харин Ю.С.</copyright-holder><copyright-holder xml:lang="en">Latushkin K.V., Kharin Y.S.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://inf.grid.by/jour/article/view/1365">https://inf.grid.by/jour/article/view/1365</self-uri><abstract><sec><title>Ц е л и</title><p>Ц е л и. Рассматриваются особенности применения двухслойных искусственных нейронных сетей в задачах аппроксимации двоичных функций многих двоичных переменных. Изучаются вопросы выбора начальных значений весов модели и количества нейронов на скрытом слое.</p></sec><sec><title>М е т о д ы</title><p>М е т о д ы. Задача аппроксимации двоичной функции с помощью искусственной нейронной сети сводится к геометрической задаче разделения вершин многомерного куба гиперплоскостями. Комбинаторными методами доказываются леммы о способах разбиения гиперкуба гиперплоскостью и строится оценка снизу количества двоичных функций, для аппроксимации которых достаточен один нейрон на скрытом слое.</p></sec><sec><title>Р е з у л ь т а т ы</title><p>Р е з у л ь т а т ы. Рассмотрены особенности задания начальных значений весов искусственной нейронной сети. Построена оценка снизу числа двоичных функций, для аппроксимации которых достаточно искусственной нейронной сети с одним нейроном на скрытом слое. Найдена алгоритмическая сложность вычисления такой оценки. Представлены численные результаты применения двухслойных искусственных нейронных сетей для аппроксимации двоичных функций в задачах защиты информации.</p></sec><sec><title>З а к л ю ч е н и е</title><p>З а к л ю ч е н и е. Результаты статьи позволяют выбирать параметры искусственной нейронной сети для повышения точности аппроксимации двоичных функций многих переменных.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>O b j e c t i v e s</title><p>O b j e c t i v e s. The article examines the features of using two-layer artificial neural network in problems of approximating binary functions of many binary variables. The issues of choosing the initial values of the model weights and choosing the number of neurons on the hidden layer are studied.</p></sec><sec><title>M e t h o d s</title><p>M e t h o d s. The problem of approximating a binary function using an artificial neural network is reduced to the geometric problem of dividing the vertices of a multidimensional cube by hyperplanes. Combinatorial methods are used to prove lemmas on ways of dividing a hypercube by a hyperplane and to construct a lower estimate for the number of binary functions that can be approximated using one neuron on the hidden layer.</p></sec><sec><title>R e s u l t s</title><p>R e s u l t s. The features of setting the initial values of weights of an artificial neural network are considered. A lower bound is constructed for the number of binary functions that can be approximated using an artificial neural network with one neuron on the hidden layer. The algorithmic complexity of calculating such an estimate is found. Numerical results are presented for using two-layer artificial neural networks to approximate binary functions in information security problems.</p></sec><sec><title>C o n c l u s i o n</title><p>C o n c l u s i o n. The results of the article allow choosing the parameters of an artificial neural network to improve the accuracy of approximation of binary functions of many variables.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>двоичная функция</kwd><kwd>комбинаторика</kwd><kwd>искусственная нейронная сеть</kwd><kwd>аппроксимация функций</kwd><kwd>генераторы псевдослучайных последовательностей</kwd></kwd-group><kwd-group xml:lang="en"><kwd>binary functions</kwd><kwd>combinatorics</kwd><kwd>artificial neural network</kwd><kwd>function approximation</kwd><kwd>pseudorandom sequence generators</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Gohr, A. Improving attacks on round-reduced speck32/64 using deep learning / A. Gohr // Advances in Cryptology – CRYPTO 2019: 39th Annual Intern. Cryptology Conf., Santa Barbara, CA, USA, 18–22 Aug. 2019. – Santa Barbara, 2019. – Pt. II. – P. 150–179.</mixed-citation><mixed-citation xml:lang="en">Gohr A. Improving attacks on round-reduced speck32/64 using deep learning. Advances in Cryptology – CRYPTO 2019: 39th Annual International Cryptology Conference, Santa Barbara, CA, USA, 18–22 August 2019, pt. II, рр. 150–179.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Deep learning-based physical side-channel analysis / S. Picek, G. Perin, L. Mariot [et al.] // ACM Computing Surveys. – 2023. – Vol. 55(11). – P. 1–35.</mixed-citation><mixed-citation xml:lang="en">Picek S., Perin G., Mariot L., Wu L., Batina L. Deep learning-based physical side-channel analysis. ACM Computing Surveys, 2023, vol. 55(11), pp. 1–35.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Boanca, S. Exploring patterns and assessing the security of pseudorandom number generators with machine learning / S. Boanca // 16th Intern. Conf. on Agents and Artificial Intelligence, Rome, Italy, 24–26 Febr. 2024. – Rome, 2024. – Vol. 3. – P. 186–193.</mixed-citation><mixed-citation xml:lang="en">Boanca S. Exploring patterns and assessing the security of pseudorandom number generators with machine learning. 16th International Conference on Agents and Artificial Intelligence, Rome, Italy, 24–26 February 2024, vol. 3, рр. 186–193.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Бетелин, В. Б. Математические задачи, связанные с искусственным интеллектом и искусственными нейронными сетями / В. Б. Бетелин, В. А. Галкин // Успехи кибернетики. – 2021. – Т. 2, № 4. – С. 6–14. – DOI: 10.51790/2712-9942-2021-2-4-1.</mixed-citation><mixed-citation xml:lang="en">Betelin V. B., Galkin V. A. Mathematical problems of artificial intelligence and artificial neural networks. Uspekhi kibernetiki [Russian Journal of Cybernetics], 2021, vol. 2, no. 4, pp. 6–14 (In Russ.). DOI: 10.51790/2712-9942-2021-2-4-1.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Николенко, С. Глубокое обучение. Погружение в мир нейронных сетей / С. Николенко, А. Кадурин, Е. Архангельская. – СПб. : Питер, 2018. – 480 с.</mixed-citation><mixed-citation xml:lang="en">Nikolenko S., Kadurin A., Arkhangelskaya E. Glubokoe obuchenie. Pogruzhenie v mir nejronnyh setej. Deep Learning. Dive into the World of Neural Networks. Saint Petersburg, Piter, 2018, 480 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Glorot, X. Understanding the difficulty of training deep feedforward neural networks / X. Glorot, Y. Bengio // Proc. of the Thirteenth Intern. Conf. on Artificial Intelligence and Statistics, Sardinia, Italy, 13–15 May 2010. – Sardinia, 2010. – Vol. 9. – P. 249–256.</mixed-citation><mixed-citation xml:lang="en">Glorot X., Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 13–15 May 2010, vol. 9, рр. 249–256.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Delving deep into rectifiers: surpassing human-level performance on ImageNet classification / K. He, X. Zhang, S. Ren, J. Sun // Proc. of the 2015 IEEE Intern. Conf. on Computer Vision, Santiago, Chile, 7–13 Dec. 2015. – Santiago, 2015. – P. 1026–1034.</mixed-citation><mixed-citation xml:lang="en">He K., Zhang X., Ren S., Sun J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015, рр. 1026–1034.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Криптология / Ю. С. Харин, С. В. Агиевич, Д. В. Васильев, Г. В. Матвеев. – Минск : БГУ, 2023. – 511 с.</mixed-citation><mixed-citation xml:lang="en">Kharin Yu. S., Agievich S. V., Vasilyev D. V., Matveev G. V. Kriptologiya. Cryptology. Minsk, Belorusskij gosudarstvennyj universitet, 2023, 511 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Dubrova, E. A list of maximum period NLFSRs / E. Dubrova // Cryptology ePrint Archive. – 2012. – URL: https://eprint.iacr.org/2012/166 (date of access: 18.04.2025).</mixed-citation><mixed-citation xml:lang="en">Dubrova E. A list of maximum period NLFSRs. Cryptology ePrint Archive, 2012. Available at: https://eprint.iacr.org/2012/166 (accessed 18.04.2025).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Программирование алгоритмов защиты информации / А. В. Домашев, М. М. Грунтович, В. О. Попов [и др.]. – М. : Нолидж, 2002. – 416 с.</mixed-citation><mixed-citation xml:lang="en">Domashev A. V., Gruntovich M. M., Popov V. O., Pravikov D. I., Shcherbakov A. Y., Prokofyev I. V. Programmirovanie algoritmov zashhity informacii. Programming of Information Security Algorithms. Moscow, Nolidzh, 2002, 416 p. (In Russ.).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
