Exploring new scenarios of adversarial attacks on pattern recognition neural networks in the context of finding new defense methods

Authors and copyright holders:

• Dyudyun G. D. , North Caucasus Federal University (Stavropol, Russia)
• Lapina M. A. , North Caucasus Federal University (Stavropol, Russia)
• Babenko M. G. , North Caucasus Federal University (Stavropol, Russia)

• 1. Szegedy C., Zaremba W., Sutskever I., Bruna J., Erhan D., Goodfellow I., Fergus R. Intriguing properties of neural networks arXiv preprint arXiv:1312.6199.2013.
• 2. Goodfellow I.J., Shlens J., Szegedy C. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.2014.
• 3. Papernot N., McDaniel P, Jha S., Fredrikson M., Celik Z.B., Ananthram Swami. The limitations of deep learning in adversarial settings. 2016 IEEE European symposium on security and privacy (EuroS&P), IEEE, 2016, рр. 372–387.
• 4. Madry A., Makelov A., Schmidt L., Tsipras D., Vladu A. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083.2017.
• 5. Xu H., Ma Y., Liu H., Deb D., Liu H., Tang J., Jain A.K. Adversarial attacks and defenses in images, graphs and text: A review. International Journal of Automation and Computing. 2020. vol. 17, рр. 151–178.
• 6. Ciresan D., Meier U., Masci J., Schmidhuber J. Multicolumn deep neural network for traffic sign classification Neural Networks, vol. 32, 2012, pp. 333–338.
• 7. Ivanyuk V.A. Neural networks and their analysis. Chronoeconomics. 2021, no. 4 (32). URL: https://cyberleninka.ru/article/n/neyronnye-seti-i-ih-analiz, free (Accessed: September 28, 2023).
• 8. Kachagina K.S., Safarova A.D. Neuron networks – development prospects. E-Scio. 2021, no. 2 (53). URL: https://cyberleninka.ru/article/n/neyronnye-seti-perspektivyrazvitiya, free (Accessed: September 28, 2023).
• 9. Kotlyarov D.V., Dyudyun G.D., Rzhevskaya N.V., Lapina M.A., Babenko M.G. Investigation of adversarial attacks on pattern recognition neural networks. Proceedings of the Institute for System Programming of the RAS, – 2023, vol. 35, no. 2, pp. 35–48. URL: http://syrcose.ispras.ru/2023/submissions/SYRCoSE_2023_paper_1044.pdf., free (Accessed: September 28, 2023).
• 10. Lapina M.A., Rzhevskaya N.V., Kotlyarov D.V., Dyudyun G.D. Features of organization of attacks on neural networks for pattern recognition. Auditorium. 2023, no. 2 (38). pp. 97–103 (in Russ.). URL: https://www.elibrary.ru/item.asp?id=54117348, free (Accessed: September 28, 2023).
• 11. Lapina M.A., Dyudyun G.D., Kotlyarov D.V. Analysis of methods for detecting adversarial attacks on deep neural networks. Proceedings of the VIII International Scientific and Practical Conference «Distance Education Technologies», «DET-2023», section «Information Security and Cyber Resistance», September 19–21, 2023, Yalta, рр. 345–348. (in Russ.) URL: http://elibrary.ru/item.asp?id=54606341, free (Accessed: September 28, 2023).
• 12. Lapina M.A., Dyudyun G.D., Kotlyarov D.V., Rjevskaya N., Subramanian S.J. Analysis of an existing method for detecting adversarial attacks on deep neural networks. Current Problems of Applied Mathematics and Computer Systems. CPAMCS 2023. Lecture Notes in Networks and Systems, vol. 1044. Springer, Cham. URL: https://doi.org/ 10.1007/978-3-031-64010-0_29, free (Accessed: September 28, 2023).