PROTECTION AGAINST ADVERSARIAL ATTACKS ON IMAGE RECOGNITION SYSTEMS USING AN AUTOENCODER
N. M. Grigorjeva, V. V. Platonov Saint Petersburg Electrotechnical University "LETI", Peter the Great St. Petersburg Polytechnic University (SPbPU)
Annotation: Considered adversarial attacks on systems of artificial neural networks for image recognition. To increase the security of image recognition systems from adversarial attacks (avoidance attacks), the use of auto-encoders is proposed. Various attacks are considered and software prototypes of autoencoders of fully connected and convolutional architectures are developed as a means of protection against evasion attacks. The possibility of using the developed prototypes as a basis for designing autoencoders for more complex architectures is substantiated.