Are GAN-based Morphs Threatening Face Recognition?
This addresses security concerns in biometric applications like border control, but is incremental as it builds on existing morphing attack research by introducing new datasets and tools.
The paper tackles the threat of GAN-based morphing attacks on face recognition systems by providing two datasets and code for four types of morphs, and finds that StyleGAN 2 morphs, despite being visually appealing, are less threatening than simpler landmark-based morphs in experiments on four state-of-the-art systems.
Morphing attacks are a threat to biometric systems where the biometric reference in an identity document can be altered. This form of attack presents an important issue in applications relying on identity documents such as border security or access control. Research in generation of face morphs and their detection is developing rapidly, however very few datasets with morphing attacks and open-source detection toolkits are publicly available. This paper bridges this gap by providing two datasets and the corresponding code for four types of morphing attacks: two that rely on facial landmarks based on OpenCV and FaceMorpher, and two that use StyleGAN 2 to generate synthetic morphs. We also conduct extensive experiments to assess the vulnerability of four state-of-the-art face recognition systems, including FaceNet, VGG-Face, ArcFace, and ISV. Surprisingly, the experiments demonstrate that, although visually more appealing, morphs based on StyleGAN 2 do not pose a significant threat to the state to face recognition systems, as these morphs were outmatched by the simple morphs that are based facial landmarks.