Investigation of Adversarial Attacks on Pattern Recognition Neural Networks

Investigation of Adversarial Attacks on Pattern Recognition Neural Networks

Denis Vladimirovich KOTLYAROV, Gleb Dmitrievich DYUDYUN, Natalya Vitalievna RZHEVSKAYA, Maria Anatolyevna LAPINA, Mikhail BABENKO

Abstract

This article discusses the algorithm for creating a neural network based on pattern recognition. Several types of attacks on neural networks are considered, the main features of such attacks are described. An analysis of the Adversarial attack was carried out. The results of experimental testing of the proposed attack are presented. Confirmation of the hypothesis about the decrease in the accuracy of recognition of the neural network during the implementation of the attack by an attacker was obtained.

Keywords

neural network, machine learning, pattern recognition, artificial intelligence, attack algorithm, information security, Adversarial attack, malicious machine learning

Edition

Proceedings of the Institute for System Programming, vol. 35, issue 2, 2023, 35-48

ISSN 2220-6426 (Online), ISSN 2079-8156 (Print).

DOI: 10.15514/ISPRAS-2023-35(2)-3

For citation

Denis Vladimirovich KOTLYAROV, Gleb Dmitrievich DYUDYUN, Natalya Vitalievna RZHEVSKAYA, Maria Anatolyevna LAPINA, Mikhail BABENKO Investigation of Adversarial Attacks on Pattern Recognition Neural Networks. Proceedings of the Institute for System Programming, vol. 35, issue 2, 2023, 35-48 DOI: 10.15514/ISPRAS-2023-35(2)-3.

Full text of the paper in pdf Back to the contents of the volume