Fingerprint Spoof Generation Using Style Transfer

Nowadays, biometrics is becoming more and more present in our everyday lives. They are used in ID documents, border controls, authentication, and e-payment, etc. Therefore, ensuring the security of biometric systems has become a major concern. The certification process aims at qualifying the behavior of a biometric system and verifying its conformity to international specifications. It involves the evaluation of the system performance and its robustness to attacks. Anti-spoofing tests require the creation of physical presentation attack instruments (PAIs), which are used to evaluate the robustness of biometric systems against spoofing through multiple attempts of testing on the device. In this article, we propose a new solution based on deep learning to generate synthetic fingerprint spoof images from a small dataset of real-life images acquired by a specific sensor. We artificially modify these images to simulate how they would appear if generated from known spoof materials usually involved in fingerprint spoofing tests. Experiments on LivDet datasets show first, that synthetic fingerprint spoof images give similar performance to real-life ones from a matching point of view only and second, that injection attacks succeed 50% of the time for most of the materials we tested.