Caldeira, Eduarda ; Neto, Pedro C. ; Gonçalves, Tiago ; Damer, Naser ; Sequeira, Ana F. ; Cardoso, Jaime S. (2024)
Disentangling morphed identities for face morphing detection.
In: Science Talks, 10
doi: 10.1016/j.sctalk.2024.100331
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
Morphing attacks keep threatening biometric systems, especially face recognition systems. Over time they have become simpler to perform and more realistic, as such, the usage of deep learning systems to detect these attacks has grown. At the same time, there is a constant concern regarding the lack of interpretability of deep learning models. Balancing performance and interpretability has been a difficult task for scientists. However, by leveraging domain information and proving some constraints, we have been able to develop IDistill, an interpretable method with state-of-the-art performance that provides information on both the identity separation on morph samples and their contribution to the final prediction. The domain information is learnt by an autoencoder and distilled to a classifier system in order to teach it to separate identity information. When compared to other methods in the literature it outperforms them in three out of five databases and is competitive in the remaining.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Caldeira, Eduarda ; Neto, Pedro C. ; Gonçalves, Tiago ; Damer, Naser ; Sequeira, Ana F. ; Cardoso, Jaime S. |
| Art des Eintrags: | Bibliographie |
| Titel: | Disentangling morphed identities for face morphing detection |
| Sprache: | Englisch |
| Publikationsjahr: | Juni 2024 |
| Verlag: | Elsevier |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Science Talks |
| Jahrgang/Volume einer Zeitschrift: | 10 |
| DOI: | 10.1016/j.sctalk.2024.100331 |
| Kurzbeschreibung (Abstract): | Morphing attacks keep threatening biometric systems, especially face recognition systems. Over time they have become simpler to perform and more realistic, as such, the usage of deep learning systems to detect these attacks has grown. At the same time, there is a constant concern regarding the lack of interpretability of deep learning models. Balancing performance and interpretability has been a difficult task for scientists. However, by leveraging domain information and proving some constraints, we have been able to develop IDistill, an interpretable method with state-of-the-art performance that provides information on both the identity separation on morph samples and their contribution to the final prediction. The domain information is learnt by an autoencoder and distilled to a classifier system in order to teach it to separate identity information. When compared to other methods in the literature it outperforms them in three out of five databases and is competitive in the remaining. |
| Freie Schlagworte: | Biometrics, Explainability, Face recognition, Knowledge distillation, Morphing attack detection, Synthetic data |
| Zusätzliche Informationen: | Art.No.: 100331 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphisch-Interaktive Systeme |
| Hinterlegungsdatum: | 30 Apr 2024 09:07 |
| Letzte Änderung: | 15 Aug 2024 11:04 |
| PPN: | 520686853 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum