Adversarial label flips attack on support vector machines

Han Xiao, Huang Xiao, Claudia Eckert

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

176 Scopus citations

Abstract

To develop a robust classification algorithm in the adversarial setting, it is important to understand the adversary's strategy. We address the problem of label flips attack where an adversary contaminates the training set through flipping labels. By analyzing the objective of the adversary, we formulate an optimization framework for finding the label flips that maximize the classification error. An algorithm for attacking support vector machines is derived. Experiments demonstrate that the accuracy of classifiers is significantly degraded under the attack.

Original languageEnglish
Title of host publicationECAI 2012 - 20th European Conference on Artificial Intelligence, 27-31 August 2012, Montpellier, France - Including Prestigious Applications of Artificial Intelligence (PAIS-2012) System Demonstration
PublisherIOS Press BV
Pages870-875
Number of pages6
ISBN (Print)9781614990970
DOIs
StatePublished - 2012
Event20th European Conference on Artificial Intelligence, ECAI 2012 - Montpellier, France
Duration: 27 Aug 201231 Aug 2012

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume242
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference20th European Conference on Artificial Intelligence, ECAI 2012
Country/TerritoryFrance
CityMontpellier
Period27/08/1231/08/12

Fingerprint

Dive into the research topics of 'Adversarial label flips attack on support vector machines'. Together they form a unique fingerprint.

Cite this