Digitally synthetized fingerprint spoofs: a threat for anti-spoofing systems?

Abdarahmane Wone (1) , Joël di Manno (2) , Christophe Rosenberger (1) , Christophe Charrier (1)

1 Equipe SAFE - Laboratoire GREYC - UMR6072
2 FIME EMEA

Ensuring security on biometric systems has always been a high priority concern. Certification of biometric systems involves the testing of the system's performance and its resistance to spoof attacks. The anti-spoofing test implies the creation and scan of multiples physical spoofs. This requests laboratory expertise and high amount of time for spoofs creation. In this paper, we propose a new solution based on deep learning to translate genuine fingerprint images and transform them into what they would look like if they were created from known spoof materials usually involved in fingerprint spoofing tests. Digitally Synthetized Fingerprint Spoofs (DSFS) help to cover a larger number of spoofs materials than it would be possible to physically fabricate in a given time. Validation method shows that synthetized images are as good as real spoofs considering their quality.

Mots clés: Biometrics; Presentation Attack Detection; style transfer; Deep learning; Generative Adversarial Networks; Presentation Attack Instruments

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

Abdarahmane Wone, Joël di Manno, Christophe Rosenberger, Christophe Charrier. Digitally synthetized fingerprint spoofs: a threat for anti-spoofing systems?. 2022 International Conference on Cyberworlds, Sep 2022, Kanazawa, Japan. ⟨hal-03748579⟩