Using Local Convolutional Units to Defend against Adversarial Examples
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10408042" target="_blank" >RIV/00216208:11320/19:10408042 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/IJCNN.2019.8852393" target="_blank" >https://doi.org/10.1109/IJCNN.2019.8852393</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/IJCNN.2019.8852393" target="_blank" >10.1109/IJCNN.2019.8852393</a>
Alternative languages
Result language
angličtina
Original language name
Using Local Convolutional Units to Defend against Adversarial Examples
Original language description
Deep neural networks are known to be sensitive to adversarial examples - inputs that are created in such a way that they are similar (if viewed by people) to clean inputs, but the neural network has high confidence that they belong to another class.In this paper, we study a new type of neural network unit similar to the convolutional units, but with a more local behavior. The unit is based on the Gaussian radial basis function. We show that if we replace the first convolutional layer in a convolutional network by the new layer (called RBFolutional), we obtain better robustness towards adversarial samples on the MNIST and CIFAR10 datasets, without sacrificing the performance on the clean examples.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GJ17-10090Y" target="_blank" >GJ17-10090Y: Network Optimization</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2019 International Joint Conference on Neural Networks (IJCNN)
ISBN
978-1-72811-985-4
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
1-8
Publisher name
IEEE
Place of publication
Neuveden
Event location
Budapešť, Maďarsko
Event date
Jul 14, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—