Logo des Repositoriums
 
Konferenzbeitrag

Transferability Analysis of an Adversarial Attack on Gender Classification to Face Recognition

Lade...
Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2021

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

Modern biometric systems establish their decision based on the outcome of machine learning (ML) classifiers trained to make accurate predictions. Such classifiers are vulnerable to diverse adversarial attacks, altering the classifiers' predictions by adding a crafted perturbation. According to ML literature, those attacks are transferable among models that perform the same task. However, models performing different tasks, but sharing the same input space and the same model architecture, were never included in transferability scenarios. In this paper, we analyze this phenomenon for the special case of VGG16-based biometric classifiers. Concretely, we study the effect of the white-box FGSM attack, on a gender classifier and compare several defense methods as countermeasure. Then, in a black-box manner, we attack a pre-trained face recognition classifier using adversarial images generated by the FGSM. Our experiments show that this attack is transferable from a gender classifier to a face recognition classifier where both were independently trained.

Beschreibung

Rezgui, Zohra; Bassit, Amina (2021): Transferability Analysis of an Adversarial Attack on Gender Classification to Face Recognition. BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5468. ISBN: 978-3-88579-709-8. pp. 125-136. Regular Research Papers. International Digital Conference. 15.-17. September 2021

Zitierform

DOI

Tags