This article will discuss the use of attacks on a neural network trained on audio data, as well as possible methods of protection against these attacks. FGSM, PGD and CW attacks, as well as data poisoning, will be considered. Within the framework of protection, Art-IBM and advertorch libraries will be considered. The obtained accuracy metrics within the framework of attack applications are presented
Cite
@article{arxiv.2412.20529,
title = {Attacks on the neural network and defense methods},
author = {A. Korenev and G. Belokrylov and B. Lodonova and A. Novokhrestov},
journal= {arXiv preprint arXiv:2412.20529},
year = {2024}
}