Vulnerability of machine learning models to adversarial examples
by
Petra Vidnerová
,
Roman Neruda
BibTeX
@MISC{Vidnerová_vulnerabilityof,
author = {Petra Vidnerová and Roman Neruda},
title = {Vulnerability of machine learning models to adversarial examples},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract: 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.
