Show simple item record

dc.contributor.authorZhang, P
dc.contributor.authorWang, J
dc.contributor.authorSun, J
dc.contributor.authorDong, G
dc.contributor.authorWang, X
dc.contributor.authorWang, X
dc.contributor.authorDong, JS
dc.contributor.authorDai, T
dc.date.accessioned2020-11-18T03:06:40Z
dc.date.available2020-11-18T03:06:40Z
dc.date.issued2020
dc.identifier.isbn9781450371216
dc.identifier.issn0270-5257
dc.identifier.doi10.1145/3377811.3380331
dc.identifier.urihttp://hdl.handle.net/10072/399420
dc.description.abstractAlthough deep neural networks (DNNs) have demonstrated astonishing performance in many applications, there are still concerns on their dependability. One desirable property of DNN for applications with societal impact is fairness (i.e., non-discrimination). In this work, we propose a scalable approach for searching individual discriminatory instances of DNN. Compared with state-of-the-art methods, our approach only employs lightweight procedures like gradient computation and clustering, which makes it significantly more scalable than existing methods. Experimental results show that our approach explores the search space more effectively (9 times) and generates much more individual discriminatory instances (25 times) using much less time (half to 1/7).
dc.description.peerreviewedYes
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.ispartofconferencenameACM/IEEE 42nd International Conference on Software Engineering (ICSE 2020)
dc.relation.ispartofconferencetitleProceedings 2020 ACM/IEEE 42nd International Conference on Software Engineering, ICSE 2020
dc.relation.ispartofdatefrom2020-06-27
dc.relation.ispartofdateto2020-07-19
dc.relation.ispartoflocationSeoul, South Korea
dc.relation.ispartofpagefrom949
dc.relation.ispartofpageto960
dc.subject.fieldofresearchArtificial intelligence
dc.subject.fieldofresearchcode4602
dc.titleWhite-box fairness testing through adversarial sampling
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationZhang, P; Wang, J; Sun, J; Dong, G; Wang, X; Wang, X; Dong, JS; Dai, T, White-box fairness testing through adversarial sampling, Proceedings 2020 ACM/IEEE 42nd International Conference on Software Engineering, ICSE 2020, 2020, pp. 949-960
dc.date.updated2020-11-18T03:03:55Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© ACM, 2020. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ICSE '20: Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering, ISBN: 978-1-4503-7121-6, https://doi.org/10.1145/3377811.3380331
gro.hasfulltextFull Text
gro.griffith.authorDong, Jin-Song


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record