TU Darmstadt / ULB / TUbiblio

ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks by Attack Re-generation

Damer, Naser ; Raja, Kiran ; Süßmilch, Marius ; Venkatesh, Sushma ; Boutros, Fadi ; Fang, Meiling ; Kirchbuchner, Florian ; Ramachandra, Raghavendra ; Kuijper, Arjan (2021)
ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks by Attack Re-generation.
16th International Symposium on Visual Computing. virtual Conference (04.-06.10.2021)
doi: 10.1007/978-3-030-90439-5_20
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

Face morphing attacks aim at creating face images that are verifiable to be the face of multiple identities, which can lead to building faulty identity links in operations like border checks. While creating a morphed face detector (MFD), training on all possible attack types is essential to achieve good detection performance. Therefore, investigating new methods of creating morphing attacks drives the generalizability of MADs. Creating morphing attacks was performed on the image level, by landmark interpolation, or on the latent-space level, by manipulating latent vectors in a generative adversarial network. The earlier results in varying blending artifacts and the latter results in synthetic-like striping artifacts. This work presents the novel morphing pipeline, ReGenMorph, to eliminate the LMA blending artifacts by using a GAN-based generation, as well as, eliminate the manipulation in the latent space, resulting in visibly realistic morphed images compared to previous works. The generated ReGenMorph appearance is compared to recent morphing approaches and evaluated for face recognition vulnerability and attack detectability, whether as known or unknown attacks.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2021
Autor(en): Damer, Naser ; Raja, Kiran ; Süßmilch, Marius ; Venkatesh, Sushma ; Boutros, Fadi ; Fang, Meiling ; Kirchbuchner, Florian ; Ramachandra, Raghavendra ; Kuijper, Arjan
Art des Eintrags: Bibliographie
Titel: ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks by Attack Re-generation
Sprache: Englisch
Publikationsjahr: 2021
Verlag: Springer
Buchtitel: Advances in Visual Computing
Reihe: Lecture Notes in Computer Science
Band einer Reihe: 13017
Veranstaltungstitel: 16th International Symposium on Visual Computing
Veranstaltungsort: virtual Conference
Veranstaltungsdatum: 04.-06.10.2021
DOI: 10.1007/978-3-030-90439-5_20
Kurzbeschreibung (Abstract):

Face morphing attacks aim at creating face images that are verifiable to be the face of multiple identities, which can lead to building faulty identity links in operations like border checks. While creating a morphed face detector (MFD), training on all possible attack types is essential to achieve good detection performance. Therefore, investigating new methods of creating morphing attacks drives the generalizability of MADs. Creating morphing attacks was performed on the image level, by landmark interpolation, or on the latent-space level, by manipulating latent vectors in a generative adversarial network. The earlier results in varying blending artifacts and the latter results in synthetic-like striping artifacts. This work presents the novel morphing pipeline, ReGenMorph, to eliminate the LMA blending artifacts by using a GAN-based generation, as well as, eliminate the manipulation in the latent space, resulting in visibly realistic morphed images compared to previous works. The generated ReGenMorph appearance is compared to recent morphing approaches and evaluated for face recognition vulnerability and attack detectability, whether as known or unknown attacks.

Freie Schlagworte: Biometrics, Face recognition, Morphing attack, Deep learning, Machine learning
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing
Hinterlegungsdatum: 10 Dez 2021 09:57
Letzte Änderung: 10 Dez 2021 09:57
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen