PPR: Enhancing Dodging Attacks while Maintaining Impersonation Attacks on Face Recognition Systems

arXiv:2401.08903v2 Announce Type: replace-cross
Abstract: Adversarial Attacks on Face Recognition (FR) encompass two types: impersonation attacks and evasion attacks. We observe that achieving a successful impersonation attack on FR does not necessarily ensure a successful dodging attack on FR in the black-box setting. Introducing a novel attack method named Pre-training Pruning Restoration Attack (PPR), we aim to enhance the performance of dodging attacks whilst avoiding the degradation of impersonation attacks. Our method employs adversarial example pruning, enabling a portion of …

abstract adversarial adversarial attacks arxiv attacks box cs.cv cs.lg evasion face face recognition impersonation novel observe recognition systems type types