Detection of print-based spoofing attacks
A method of assessing the possibility of an iris print-attack includes measurement of the eye movement of a person. One or more values (e.g., a feature vector) are determined based on the measured eye movements. Based on the determined values, an assessment is made of whether or not the person is engaging in an iris print-attack.
1. A method of assessing the possibility of an iris print-attack, comprising:
measuring, by a sensing device, eye movement of a person;
decomposing the measured eye movement signals into elementary units;
determining, by a biometric assessment system implemented on one or more computing devices, one or more statistic measures related to the global and/or local distortions, wherein the statistic measures are determined from the elementary units;
assessing, by the biometric assessment system, based at least in part on at least one of the determined statistic measures, whether or not the statistic measurements indicate that the measured person is utilizing an iris paper-print.
2. The method of claim 1 , wherein assessing whether or not the person is engaging in a print iris attack comprises determining whether one or more of the statistic measurements are above or below a predetermined threshold.
3. The method of claim 1 , wherein at least one of the global and/or local distortions comprises artifacts appearing during eye tracking measurements obtained during measuring eye movement of the person.
4. The method of claim 3 , wherein the artifacts appearing during eye tracking measurements comprise inconsistent positioning of the pupil center and the corneal reflection.
5. The method of claim 1 , wherein at least one of the global distortions comprises global positional offset.
6. The method of claim 1 , wherein at least one of the local distortions comprise abnormal local amplitude variations manifested as irregular differences of amplitude levels in parts of the signal.
7. The method of claim 1 , wherein at least one of the global and/or local distortions comprises the presence of enhanced levels of noise contaminating signals captured during measuring of the eye movement of the person.
8. The method of claim 1 , wherein the elementary units are determined using a Velocity Threshold Identification technique.
9. The method of claim 1 , wherein the statistical measures comprise one or more of: local unit centroid; local unit power; local unit variance; local unit signal-to-noise ratio; and local unit invalidity, wherein each of the statistical measures are calculated for each elementary unit.
10. The method of claim 9 , further comprising forming a final feature vector from the statistical measures.
11. A system, comprising:
an instrument configured to measure eye movement of a person;
a processor; and
a memory coupled to the processor, wherein the memory comprises program instructions executable by the processor to implement:
measuring, using the instrument, eye movement of the person;
decomposing the measured eye movement signals into elementary units;
determining one or more statistic measures related to the global and/or local distortions, wherein the determined statistic measures are determined from the elementary units; and
assessing, based at least in part on at least one of the determined statistic measures, whether or not the statistic measurements indicate that the measured person is utilizing an iris paper-print.
12. A non-transitory, computer-readable storage medium comprising program instructions stored thereon, wherein the program instructions are configured to implement:
measuring eye movement of the person;
decomposing the measured eye movement signals into elementary units;
determining one or more statistic measures related to the global and/or local distortions, wherein the determined statistic measures are determined from the elementary units; and
assessing, based at least in part on at least one of the determined statistic measures, whether or not the statistic measurements indicate that the measured person is utilizing an iris paper-print.
13. The system of claim 11 , wherein at least one of the global and/or local distortions comprises artifacts appearing during eye tracking measurements obtained during measuring eye movement of the person.
14. The system of claim 11 , wherein at least one of the global distortions comprises global positional offset.
15. The system of claim 11 , wherein at least one of the local distortions comprise abnormal local amplitude variations manifested as irregular differences of amplitude levels in parts of the signal.
16. The system of claim 11 , wherein at least one of the global and/or local distortions comprises the presence of enhanced levels of noise contaminating signals captured during measuring of the eye movement of the person.
17. The medium of claim 12 , wherein at least one of the global and/or local distortions comprises artifacts appearing during eye tracking measurements obtained during measuring eye movement of the person.
18. The medium of claim 12 , wherein at least one of the global distortions comprises global positional offset.
19. The medium of claim 12 , wherein at least one of the local distortions comprise abnormal local amplitude variations manifested as irregular differences of amplitude levels in parts of the signal.
20. The medium of claim 12 , wherein at least one of the global and/or local distortions comprises the presence of enhanced levels of noise contaminating signals captured during measuring of the eye movement of the person.