Logo des Repositoriums
 
Konferenzbeitrag

Toward Practical Adversarial Attacks on Face Verification Systems

Vorschaubild

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2021

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Gesellschaft für Informatik e.V.

Zusammenfassung

DNN-based face verification systems are vulnerable to adversarial examples. The previous paper's evaluation protocol (scenario), which we called the probe-dependent attack scenario, was unrealistic. We define a more practical attack scenario, the probe-agnostic attack. We empirically show that these attacks are more challenging than probe-dependent ones. We propose a simple and effective method, PAMTAM, to improve the attack success rate for probe-agnostic attacks. We show that PAMTAM successfully improves the attack success rate in a wide variety of experimental settings.

Beschreibung

Kakizaki, Kazuya; Miyagawa, Taiki; Singh, Inderjeet; Sakuma, Jun (2021): Toward Practical Adversarial Attacks on Face Verification Systems. 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. 113-124. Regular Research Papers. International Digital Conference. 15.-17. September 2021

Zitierform

DOI

Tags