Anti-discrimination Analysis Using Privacy Attack Strategies

Handle URI:
http://hdl.handle.net/10754/556651
Title:
Anti-discrimination Analysis Using Privacy Attack Strategies
Authors:
Ruggieri, Salvatore; Hajian, Sara; Kamiran, Faisal; Zhang, Xiangliang ( 0000-0002-3574-5665 )
Abstract:
Social discrimination discovery from data is an important task to identify illegal and unethical discriminatory patterns towards protected-by-law groups, e.g., ethnic minorities. We deploy privacy attack strategies as tools for discrimination discovery under hard assumptions which have rarely tackled in the literature: indirect discrimination discovery, privacy-aware discrimination discovery, and discrimination data recovery. The intuition comes from the intriguing parallel between the role of the anti-discrimination authority in the three scenarios above and the role of an attacker in private data publishing. We design strategies and algorithms inspired/based on Frèchet bounds attacks, attribute inference attacks, and minimality attacks to the purpose of unveiling hidden discriminatory practices. Experimental results show that they can be effective tools in the hands of anti-discrimination authorities.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Springer Verlag (Germany)
Journal:
Machine Learning and Knowledge Discovery in Databases
Conference/Event name:
European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2014
Issue Date:
15-Sep-2014
DOI:
10.1007/978-3-662-44851-9_44
Type:
Conference Paper
ISSN:
0302-9743
Additional Links:
http://link.springer.com/chapter/10.1007%2F978-3-662-44851-9_44
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorRuggieri, Salvatoreen
dc.contributor.authorHajian, Saraen
dc.contributor.authorKamiran, Faisalen
dc.contributor.authorZhang, Xiangliangen
dc.date.accessioned2015-06-10T11:41:12Zen
dc.date.available2015-06-10T11:41:12Zen
dc.date.issued2014-09-15en
dc.identifier.issn0302-9743en
dc.identifier.doi10.1007/978-3-662-44851-9_44en
dc.identifier.urihttp://hdl.handle.net/10754/556651en
dc.description.abstractSocial discrimination discovery from data is an important task to identify illegal and unethical discriminatory patterns towards protected-by-law groups, e.g., ethnic minorities. We deploy privacy attack strategies as tools for discrimination discovery under hard assumptions which have rarely tackled in the literature: indirect discrimination discovery, privacy-aware discrimination discovery, and discrimination data recovery. The intuition comes from the intriguing parallel between the role of the anti-discrimination authority in the three scenarios above and the role of an attacker in private data publishing. We design strategies and algorithms inspired/based on Frèchet bounds attacks, attribute inference attacks, and minimality attacks to the purpose of unveiling hidden discriminatory practices. Experimental results show that they can be effective tools in the hands of anti-discrimination authorities.en
dc.publisherSpringer Verlag (Germany)en
dc.relation.urlhttp://link.springer.com/chapter/10.1007%2F978-3-662-44851-9_44en
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/978-3-662-44851-9_44en
dc.titleAnti-discrimination Analysis Using Privacy Attack Strategiesen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalMachine Learning and Knowledge Discovery in Databasesen
dc.conference.date2014-09-15 to 2014-09-19en
dc.conference.nameEuropean Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2014en
dc.conference.locationNancy, FRAen
dc.eprint.versionPost-printen
dc.contributor.institutionUniversità di Pisa, Italyen
dc.contributor.institutionUniversitat Rovira i Virgili, Spainen
dc.contributor.institutionInformation Technology, University of the Punjab, Pakistanen
kaust.authorZhang, Xiangliangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.