Detecting Morphed Face Attacks Using Residual Noise from Deep Multi-scale Context Aggregation Network
Detecting Morphed Face Attacks Using Residual Noise from Deep Multi-scale Context Aggregation Network
复制标题
DOI：
10.1109/wacv45572.2020.9093488
复制
发表时间：
2020-01
期刊：
影响因子：
--
通讯作者：
S. Venkatesh;Raghavendra Ramachandra;K. Raja;L. Spreeuwers;R. Veldhuis;C. Busch
中科院分区：
文献类型：
--
作者：
S. Venkatesh;Raghavendra Ramachandra;K. Raja;L. Spreeuwers;R. Veldhuis;C. Busch
沿着人脸识别系统的部署，人们对这些系统容易受到包括变形攻击在内的各种攻击表示关切。变形面部攻击涉及两个不同的面部图像，以便经由变形过程获得与两个贡献数据主体充分相似的所得攻击图像。所获得的变形图像可以成功地验证两个主题视觉（由人类专家）和商业FRS。面部变形攻击对电子护照签发过程和边境控制等应用程序构成严重的安全风险，除非此类攻击被检测到并得到缓解。在这项工作中，我们提出了一种新的方法来可靠地检测变形的脸攻击使用一个新设计的demising框架。为此，我们设计并引入了一个新的深度多尺度上下文聚合网络（MS-CAN）来获得去噪图像，随后用于确定图像是否变形。在三个不同的变形人脸图像数据集上进行了大量的实验。变形攻击检测（MAD）性能的方法也对14个不同的国家的最先进的技术，使用ISO-IEC 30107-3评估指标进行基准测试。基于所获得的定量结果，所提出的方法已表明在所有三个数据集上的最佳性能，也在跨数据集实验。
Along with the deployment of the Face Recognition Systems (FRS), concerns were raised related to the vulnerability of those systems towards various attacks including morphed attacks. The morphed face attack involves two different face images in order to obtain via a morphing process a resulting attack image, which is sufficiently similar to both contributing data subjects. The obtained morphed image can successfully be verified against both subjects visually (by a human expert) and by a commercial FRS. The face morphing attack poses a severe security risk to the e-passport issuance process and to applications like border control, unless such attacks are detected and mitigated. In this work, we propose a new method to reliably detect a morphed face attack using a newly designed demising framework. To this end, we design and introduce a new deep Multi-scale Context Aggregation Network (MS-CAN) to obtain denoised images, which is subsequently used to determine if an image is morphed or not. Extensive experiments are carried out on three different morphed face image datasets. The Morphing Attack Detection (MAD) performance of the proposed method is also benchmarked against 14 different state-of-the-art techniques using the ISO-IEC 30107-3 evaluation metrics. Based on the obtained quantitative results, the proposed method has indicated the best performance on all three datasets and also on cross-dataset experiments.