Logo des Repositoriums
 

Achieving Facial De-Identification by Taking Advantage of the Latent Space of Generative Adversarial Networks

Kurzanzeige
dc.contributor.authorFrick, Raphael Antonius
dc.contributor.authorSteinebach, Martin
dc.contributor.editorGesellschaft fĂŒr Informatik e.V. (GI)
dc.date.accessioned2021-12-14T10:57:41Z
dc.date.available2021-12-14T10:57:41Z
dc.date.issued2021
dc.description.abstractThe General Data Protection Regulation (EU)2016/679 passed by the European Union prohibits any data collection and processing that was conducted without the consent of the individuals involved. Especially images showing faces are often subject to these regulations and therefore, either need to be removed or anonymized. Early approaches however were often troubled by strong visual artifacts. In this work, we propose a novel anonymization pipeline that generates a proxy face for a group of individuals by taking advantage of the semantics of the latent space of generative adversarial networks. Experiments have shown that by following a 𝑘-same approach and utilizing different clustering techniques, privacy for the individuals involved can be greatly enhanced, while preserving important facial characteristics.en
dc.identifier.doi10.18420/informatik2021-068
dc.identifier.isbn978-3-88579-708-1
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/37735
dc.language.isoen
dc.publisherGesellschaft fĂŒr Informatik, Bonn
dc.relation.ispartofINFORMATIK 2021
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-314
dc.subjectFacial De-Identification
dc.subjectk-Anonymity
dc.subjectPrivacy
dc.subjectGenerative Adversarial Networks
dc.subjectFacial Image Data
dc.titleAchieving Facial De-Identification by Taking Advantage of the Latent Space of Generative Adversarial Networksen
gi.citation.endPage806
gi.citation.startPage795
gi.conference.date27. September - 1. Oktober 2021
gi.conference.locationBerlin
gi.conference.sessiontitleWorkshop: Security, Datenschutz und Anonymisierung

Dateien

OriginalbĂŒndel
1 - 1 von 1
Vorschaubild
Name:
H1-5.pdf
GrĂ¶ĂŸe:
15.56 MB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P314 - INFORMATIK 2021 - Computer Science & Sustainability