Vulnerabilities of Unattended Face Verification Systems to Facial Components-based Presentation Attacks: An Empirical Study

Vulnerabilities of Unattended Face Verification Systems to Facial Components-based Presentation Attacks: An Empirical Study
复制标题

无人值守的人脸验证系统对基于面部成分的演示攻击的漏洞:实证研究

DOI:
10.1145/3491199
复制
发表时间:
2022-02
影响因子:
2.3
通讯作者:
Christoph Busch
Christoph Busch
中科院分区:
计算机科学4区
文献类型:
--
作者:
Le Qin;Fei Peng;Min Long;Ramach;ra Raghavendra;Christoph Busch

文献摘要

参考文献

相似文献

由于人脸呈现攻击(PA)是无人值守人脸验证系统的现实威胁,因此人脸呈现攻击检测(PAD)在过去几年中得到了深入研究,而人脸PAD的最新进展显着降低了此类攻击的成功率。本文对一种新颖有效的面部冒名顶替者 PA 进行了实证研究。在所提出的 PA 中,通过使用最脆弱的面部组件来创建面部伪影,这些组件是根据不同面部组件对冒充 PA 的脆弱性分析而优化选择的。攻击者可以通过在自己的真脸上呈现面部伪影来启动面部 PA。通过收集包含各种类型的伪影和呈现攻击工具(PAI)的 PA 数据库,实验结果和分析表明,与打印、重放和掩模 PA 相比,所提出的 PA 对人脸验证和 PAD 系统构成更严重的威胁。此外,还通过评估未知人脸验证和现实世界的 PAD 系统来研究所提出的 PA 的泛化能力和针对商业系统的漏洞分析。它为人脸PA的研究提供了新的范式。
As face presentation attacks (PAs) are realistic threats for unattended face verification systems, face presentation attack detection (PAD) has been intensively investigated in past years, and the recent advances in face PAD have significantly reduced the success rate of such attacks. In this article, an empirical study on a novel and effective face impostor PA is made. In the proposed PA, a facial artifact is created by using the most vulnerable facial components, which are optimally selected based on the vulnerability analysis of different facial components to impostor PAs. An attacker can launch a face PA by presenting a facial artifact on his or her own real face. With a collected PA database containing various types of artifacts and presentation attack instruments (PAIs), the experimental results and analysis show that the proposed PA poses a more serious threat to face verification and PAD systems compared with the print, replay, and mask PAs. Moreover, the generalization ability of the proposed PA and the vulnerability analysis with regard to commercial systems are also investigated by evaluating unknown face verification and real-world PAD systems. It provides a new paradigm for the study of face PAs.
DOI: 10.1109/tifs.2020.3026553
发表时间: 2020-09
影响因子: 6.8
作者:
Rizhao Cai;Haoliang Li;Shiqi Wang-;Changsheng Chen;A. Kot
通讯作者: Rizhao Cai;Haoliang Li;Shiqi Wang-;Changsheng Chen;A. Kot
DOI: 10.1016/j.cviu.2020.102988
发表时间: 2020-08
期刊: Comput. Vis. Image Underst.
影响因子: --
作者:
Bowen Zhang;B. Tondi;M. Barni
通讯作者: Bowen Zhang;B. Tondi;M. Barni
DOI: 10.1109/tbiom.2019.2946175
发表时间: 2020-01
期刊: IEEE Transactions on Biometrics, Behavior, and Identity Science
影响因子: --
作者:
Ketan Kotwal;Z. Mostaani;S. Marcel
通讯作者: Ketan Kotwal;Z. Mostaani;S. Marcel
DOI: 10.1109/tifs.2018.2801312
发表时间: 2018-07-01
影响因子: 6.8
作者:
Li, Haoliang;Li, Wen;Kot, Alex C.
通讯作者: Kot, Alex C.
DOI: 10.1016/j.patcog.2019.107032
发表时间: 2020-02-01
影响因子: 8
作者:
Jia, Shan;Guo, Guodong;Xu, Zhengquan
通讯作者: Xu, Zhengquan