Logo des Repositoriums
 

Adversarial learning for a robust iris presentation attack detection method against unseen attack presentations

Kurzanzeige
dc.contributor.authorFerreira, Pedro M.
dc.contributor.authorSequeira, Ana F.
dc.contributor.authorPernes, Diogo
dc.contributor.authorRebelo, Ana
dc.contributor.authorCardoso, Jaime S.
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.contributor.editorDantcheva, Antitza
dc.contributor.editorRathgeb, Christian
dc.contributor.editorUhl, Andreas
dc.date.accessioned2020-09-15T13:01:30Z
dc.date.available2020-09-15T13:01:30Z
dc.date.issued2019
dc.description.abstractDespite the high performance of current presentation attack detection (PAD) methods, the robustness to unseen attacks is still an under addressed challenge. This work approaches the problem by enforcing the learning of the bona fide presentations while making the model less dependent on the presentation attack instrument species (PAIS). The proposed model comprises an encoder, mapping from input features to latent representations, and two classifiers operating on these underlying representations: (i) the task-classifier, for predicting the class labels (as bona fide or attack); and (ii) the species-classifier, for predicting the PAIS. In the learning stage, the encoder is trained to help the task-classifier while trying to fool the species-classifier. Plus, an additional training objective enforcing the similarity of the latent distributions of different species is added leading to a ‘PAIspecies’- independent model. The experimental results demonstrated that the proposed regularisation strategies equipped the neural network with increased PAD robustness. The adversarial model obtained better loss and accuracy as well as improved error rates in the detection of attack and bona fide presentations.en
dc.identifier.isbn978-3-88579-690-9
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/34238
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofBIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-297
dc.subjectIris presentation attack detection
dc.subjectopen-set
dc.subjectadversarial learning
dc.subjecttransfer learning.
dc.titleAdversarial learning for a robust iris presentation attack detection method against unseen attack presentationsen
dc.typeText/Conference Paper
gi.citation.endPage58
gi.citation.publisherPlaceBonn
gi.citation.startPage47
gi.conference.date18.-20. September 2019
gi.conference.locationDarmstadt, Germany
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild
Name:
BIOSIG_2019_paper_25_update2.pdf
Größe:
221.35 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P296 - BIOSIG 2019 - Proceedings of the 18th International Conference of the Biometrics Special Interest Group