Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector
Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector
复制标题
DOI：
10.1109/icme.2018.8486579
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
H. Nguyen;Ngoc-Dung T. Tieu;Hoang-Quoc Nguyen-Son;J. Yamagishi;I. Echizen
中科院分区：
文献类型：
--
作者：
H. Nguyen;Ngoc-Dung T. Tieu;Hoang-Quoc Nguyen-Son;J. Yamagishi;I. Echizen
使计算机生成（CG）图像更难检测是计算机图形学和安全领域的一个有趣问题。虽然大多数方法都集中在图像渲染阶段，本文提出了一种方法的基础上增加自然的CG人脸图像的欺骗检测器的角度来看。所提出的方法是使用卷积神经网络（CNN），包括两个自编码器和一个Transformer，并使用一个黑盒训练没有梯度信息。超过50%的变换CG图像没有被三个国家的最先进的欺骗检测器检测到。这种能力对面部认证系统的可靠性提出了警告，面部认证系统在日常生活中得到了广泛的应用。
Making computer-generated (CG) images more difficult to detect is an interesting problem in computer graphics and security. While most approaches focus on the image rendering phase, this paper presents a method based on increasing the naturalness of CG facial images from the perspective of spoofing detectors. The proposed method is implemented using a convolutional neural network (CNN) comprising two autoencoders and a transformer and is trained using a black-box discriminator without gradient information. Over 50% of the transformed CG images were not detected by three state-of-the-art spoofing detectors. This capability raises an alarm regarding the reliability of facial authentication systems, which are becoming widely used in daily life.