On the Robustness of Support Vector Machines against Adversarial Examples

Authors

P. Langenberg, E. Balda, A. Behboodi, R. Mathar,

Abstract

        In this paper, the robustness of Support Vector Machines (SVMs) against adversarial instances is considered in relation to the design parameters. After generating adversarial instances using convex programming, it is shown through extensive numerical analysis that the robustness is significantly affected by parameters which change the linearity of the models. Interestingly, robustness is only slightly sensitive to the parameter determining the margin between classes. It is shown that adversarial robustness not only depends on the geometric properties of the classifier but is also subject to the accuracy of the model. The results are discussed in the light of the so-called linearity hypothesis, regarding adversarial robustness of machine learning algorithms.

BibTEX Reference Entry 

@inproceedings{LaBaBeMa19,
	author = {Peter Langenberg and Emilio Balda and Arash Behboodi and Rudolf Mathar},
	title = "On the Robustness of Support Vector Machines against Adversarial Examples",
	pages = "1-6",
	booktitle = "13th Internatioanl Symposium on Signal Processing and Communication Systems",
	address = {Gold Coast, Australia},
	month = Dec,
	year = 2019,
	hsb = RWTH-2019-11857,
	}

Downloads

 Download paper  Download bibtex-file

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights there in are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.