Real Masks and Fake Faces: On the Masked Face Presentation Attack Detection
Real Masks and Fake Faces: On the Masked Face Presentation Attack Detection
复制标题
真面具和假脸：关于蒙面人脸演示攻击检测
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Arjan Kuijper
中科院分区：
文献类型：
--
作者：
Meiling Fang;N. Damer;Florian Kirchbuchner;Arjan Kuijper
持续的 COVID-19 大流行导致了大规模的公共卫生问题。口罩已成为减少冠状病毒传播的最有效方法之一。这使得人脸识别（FR）成为一项具有挑战性的任务，因为隐藏了一些判别性特征。此外，人脸呈现攻击检测（PAD）对于确保FR系统的安全至关重要。与越来越多的蒙面 FR 研究相反，蒙面攻击对 PAD 的影响尚未得到探讨。因此，我们在演示中展示了带有真实面具的新颖攻击，以及带有戴着面具的受试者的攻击，以反映当前的现实世界情况。此外，本研究通过使用七种最先进的 PAD 算法在数据库内和跨数据库场景下研究了掩蔽攻击对 PAD 性能的影响。我们还评估了 FR 系统在屏蔽攻击方面的脆弱性。实验表明，真实的伪装攻击对FR系统的运行和安全构成严重威胁。
The ongoing COVID-19 pandemic has lead to massive public health issues. Face masks have become one of the most efficient ways to reduce coronavirus transmission. This makes face recognition (FR) a challenging task as several discriminative features are hidden. Moreover, face presentation attack detection (PAD) is crucial to ensure the security of FR systems. In contrast to growing numbers of masked FR studies, the impact of masked attacks on PAD has not been explored. Therefore, we present novel attacks with real masks placed on presentations and attacks with subjects wearing masks to reflect the current real-world situation. Furthermore, this study investigates the effect of masked attacks on PAD performance by using seven state-of-the-art PAD algorithms under intra- and cross-database scenarios. We also evaluate the vulnerability of FR systems on masked attacks. The experiments show that real masked attacks pose a serious threat to the operation and security of FR systems.