Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector
This raises an alarm about the reliability of widely used facial authentication systems, highlighting a security vulnerability.
The paper tackled the problem of making computer-generated facial images evade detection by spoofing detectors, achieving over 50% of transformed images not being detected by three state-of-the-art detectors.
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.