On the Vulnerability of Palm Vein Recognition to Spoofing Attacks

The vulnerability of palm vein recognition to spoofing at-tacks is studied in this paper. A collection of spoofing palm vein images has been created from real palm vein samples. Palm vein images are printed using a commercial printer and then, presented at a contactless palm vein sensor. Ex-periments are carried out using an extensible framework, which allows fair and reproducible benchmarks. Results are presented comparing two automatic segmentations. Ex-perimental results lead to a spoofing false accept rate of 65%, thus showing that palm vein biometrics is vulnerable to spoofing attacks, pointing out the importance to inves-tigate countermeasures against this type of fraudulent ac-tions. A study based on the number of the enrolment sam-ples is also reported, demonstrating a relationship between the number of enrolment samples and the vulnerability of the system to spoofing. 1