Evolutionary Generation of Adversarial Examples for Deep and Shallow Machine Learning Models
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F16%3A00469507" target="_blank" >RIV/67985807:_____/16:00469507 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1145/2955129.2955178" target="_blank" >http://dx.doi.org/10.1145/2955129.2955178</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/2955129.2955178" target="_blank" >10.1145/2955129.2955178</a>
Alternative languages
Result language
angličtina
Original language name
Evolutionary Generation of Adversarial Examples for Deep and Shallow Machine Learning Models
Original language description
Studying vulnerability of machine learning models to adversarial examples is an important way to understand their robustness and generalization properties. In this paper, 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 RBF 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/GA15-19877S" target="_blank" >GA15-19877S: Automated Knowledge and Plan Modeling for Autonomous Robots</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
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 of the The 3rd Multidisciplinary International Social Networks Conference on SocialInformatics 2016, Data Science 2016
ISBN
978-1-4503-4129-5
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
—
Publisher name
ACM
Place of publication
New York
Event location
New Yersey
Event date
Aug 15, 2016
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—