The team composed by Domenico Mattiello, Michela Gravina and Antonio Galli, coordinated by Stefano Marrone, Ph.D., and directed by professor Carlo Sansone, members of the PICUS group of the DIETI @ University Federico II, won first place in the LivDet2021 challenge 'Liveness Detection in Action'.
LivDet is a biennial international competition organized by the University of Cagliari, open to companies and universities and focused on the detection of counterfeit fingerprints. This year's edition was the one with the higher number of competitors (23), with teams coming from Italy, Germany, Czech Republic, the USA, South Korea and China.
The challenge won by the PICUS team focused on the development of an algorithm for the detection of forged fingerprints (e.g. obtained through molds and/or latent fingerprints of a target subject) within an authentication system based on biometrics.
The proposed solution is based on Artificial Intelligence techniques, in particular on a combination of Deep Learning and Adversarial Perturbations. The result is an algorithm that has proved capable of detecting counterfeit prints by varying the sensor (scanner) and the materials used to make the fakes, outperforming by over 5% the runner-up, proposed by a Chinese team.
The solution was presented to the scientific community on August, 7th, during the International Joint Conference on Biometrics (IJCB), the most important international conference in the field of biometric systems, jointly sponsored by the IAPR (International Association for Pattern Recognition) and the IEEE Biometrics Council.
LivDet: https://livdet.diee.
The IJCB2021 conference: http://ijcb2021.