Attacks on the neural network and defense methods
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929651543179264 |
|---|---|
| author | Korenev, A. Belokrylov, G. Lodonova, B. Novokhrestov, A. |
| author_facet | Korenev, A. Belokrylov, G. Lodonova, B. Novokhrestov, A. |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_20529 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Attacks on the neural network and defense methods Korenev, A. Belokrylov, G. Lodonova, B. Novokhrestov, A. Cryptography and Security Artificial Intelligence 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 |
| title | Attacks on the neural network and defense methods |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2412.20529 |