Vai al contenuto

Presentation Attack Detection

Fingerprint presentation attack detection is one of the most active research topic in which PRA Lab is involved.

It has been shown since from 2002 that fingerprint can be replicated using artificial materials. PRA Lab has developed a high-level skill on replicating fingerprints by very common materials, thus obtaining finger replica whose characteristic are similar to those of the finger skin and can deceive a standard fingerprint recognition system if it is not equipped of a particular presentation attack detection (PAD) algorithm.

PRA Lab proposed several algorithms for detecting the fingerprint PAD which are competitive with those in the literature. PRA Lab also co-organizes the Fingeprint Liveness Detection Competition, known as “LivDet”, hosted in prestigious international conferences. Several academic and industrial participants have been competitors at the last LivDet editions.

Thanks to the cooperation with Ra.C.I.S., namely, Raggruppamento Carabinieri Investigazioni Scientifiche, which is the Scientific Investigation Office of Arma dei Carabinieri in Italy, PRA Lab developed a tool for fingerprint processing and enhancement, including some algorithms to detect presentation attacks from latent fingerprint images.

Latest Releted Publications

Active projects

Fingerprint Liveness Detection Competition

In order to cover the lack of common data and protocols to assess the performance of fingerprint presentation attack detection (PAD) systems, the Biometric Unit organized the International Fingerprint Liveness Detection Competition (LivDet) since from 2009. The LivDet competitions aim to assess the performance of fingerprint PAD algorithms using a common experimental protocol and data sets. The competition is open to academic and industrial institutions which have developed fingerprint PAD algorithms.

Biometrics research topics


Personal authentication

Personal recognition through physiological and behavioral characteristics.


Presentation attacks

Protect biometric systems from attacks targeting the sensor.


DeepFake detection

Detection of facial identities manipulations in video and images.


Crowd Analysis

Anomaly detection in crowd analysis refers to the ability to detect events that deviate from normality.


Multimodal biometrics

Combining information coming from different biometric traits and soft-biometrics.


Behavioral biometrics

Analysis of behavior and biomedical signals in the biometric domain.