CASPIAN JOURNAL

MANAGEMENT AND HIGH TECHNOLOGIES

CLASSIFICATION OF ATTACK MECHANISMS AND RESEARCH OF PROTECTION METHODS FOR SYSTEMS USING MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE ALGORITHMS

Read

Volodin Ilya V., Putyato Michael M., Makaryan Alexander S., Evglevsky Vyacheslav Yu. CLASSIFICATION OF ATTACK MECHANISMS AND RESEARCH OF PROTECTION METHODS FOR SYSTEMS USING MACHINE LEARNING AND ARTIFICIAL INTELLIGENCE ALGORITHMS // Caspian journal : management and high technologies. — 2021. — №2. — pp. 91-98.

Volodin Ilya V. - Kuban State Technological University, ilya.volodin.02@mail.ru

Putyato Michael M. - Kuban State Technological University, putyato.m@gmail.com

Makaryan Alexander S. - Kuban State Technological University, msanya@yandex.ru

Evglevsky Vyacheslav Yu. - Kuban State Technological University, evglevsky-v@mail.ru

This article provides a complete classification of attacks using artificial intelligence. Three main identified sections were considered: attacks on information systems and computer networks, attacks on artificial intelligence models (poisoning attacks, evasion attacks, extraction attacks, privacy attacks), attacks on human consciousness and opinion (all types of deepfake). In each of these sections, the mechanisms of attacks were identified and studied, in accordance with them, the methods of protection were set. In conclusion, a specific example of an attack using a pretrained model was analyzed and protected against it using the method of modifying the input data, namely, image compression in order to get rid of extraneous noise.

Key words: artificial intelligence, neural networks, deep learning, machine learning cybersecurity, machine learning model, poisoning attacks, evasion attacks, privacy attacks, model extraction attacks, deepfake