P315 - BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group

Auflistung nach:

1 - 1 von 1

Konferenzbeitrag
Toward Practical Adversarial Attacks on Face Verification Systems
(BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Kakizaki, Kazuya; Miyagawa, Taiki; Singh, Inderjeet; Sakuma, Jun
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.