Vulnerability of Machine Learning Models to Adversarial Examples
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F16%3A00462893" target="_blank" >RIV/67985807:_____/16:00462893 - isvavai.cz</a>
Result on the web
<a href="http://ceur-ws.org/Vol-1649/187.pdf" target="_blank" >http://ceur-ws.org/Vol-1649/187.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Vulnerability of Machine Learning Models to Adversarial Examples
Original language description
We propose a genetic algorithm for generating adversarial examples for machine learning models. Such approach is able to find adversarial examples without the access to model’s parameters. Different models are tested, including both deep and shallow neural networks architectures. We show that RBF networks and SVMs with Gaussian kernels tend to be rather robust and not prone to misclassification of adversarial examples.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/GA15-18108S" target="_blank" >GA15-18108S: Model complexity of neural, radial, and kernel networks</a><br>
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2016
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings ITAT 2016: Information Technologies - Applications and Theory
ISBN
978-1-5370-1674-0
ISSN
1613-0073
e-ISSN
—
Number of pages
8
Pages from-to
187-194
Publisher name
Technical University & CreateSpace Independent Publishing Platform
Place of publication
Aachen & Charleston
Event location
Tatranské Matliare
Event date
Sep 15, 2016
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—