Logo des Repositoriums
 

Towards Generating High Definition Face Images from Deep Templates

Kurzanzeige
dc.contributor.authorDong, Xingbo
dc.contributor.authorJin, Zhe
dc.contributor.authorGuo, Zhenhua
dc.contributor.authorTeoh, Andrew Beng Jin
dc.contributor.editorBrömme, Arslan
dc.contributor.editorBusch, Christoph
dc.contributor.editorDamer, Naser
dc.contributor.editorDantcheva, Antitza
dc.contributor.editorGomez-Barrero, Marta
dc.contributor.editorRaja, Kiran
dc.contributor.editorRathgeb, Christian
dc.contributor.editorSequeira, Ana
dc.contributor.editorUhl, Andreas
dc.date.accessioned2021-10-04T08:43:53Z
dc.date.available2021-10-04T08:43:53Z
dc.date.issued2021
dc.description.abstractFace recognition based on deep convolutional neural networks (CNN) has manifested superior accuracy. Despite the high discriminability of deep features generated by CNN, the vulnerability of the deep feature is often overlooked and leads to security and privacy concerns, particularly, the risks of reconstructing face images from the deep templates. In this paper, we propose a method to generate high definition (HD) face images from deep features. To be specific, the deep features extracted from CNN are mapped to the input (latent vector) of the pre-trained StyleGAN2 using a regression model. Subsequently, HD face images can be generated based on the latent vector by the pre-trained StyleGAN2 model. To evaluate our method, we derived the face features from the generated HD face images and compared against the bona fide face features. In the sense of face image reconstruction, our method is simple, yet the experimental results suggest the effectiveness, which achieves an attack performance as high as TAR=46.08% (18.30%) @ FAR=0.1 threshold under type-I (type-II) attack settings. Besides, experiment results also indicate that 50.7% of generated HD face images can pass one commercial off-the-shelf (COTS) liveness detection.en
dc.identifier.isbn978-3-88579-709-8
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/37474
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofBIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-315
dc.subjectFace template security
dc.subjectFace images reconstruction
dc.subjectFeatures to face images
dc.titleTowards Generating High Definition Face Images from Deep Templatesen
dc.typeText/Conference Paper
gi.citation.endPage80
gi.citation.publisherPlaceBonn
gi.citation.startPage71
gi.conference.date15.-17. September 2021
gi.conference.locationInternational Digital Conference
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
biosig2021_proceedings_08.pdf
Größe:
771.94 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P315 - BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group