Systems and methods for spoof detection and liveness analysis
Spoof-detection and liveness analysis is performed using a software-based solution on a user device, such as a smartphone having a camera, audio output component (e.g., earpiece), and audio input component (e.g., microphone). One or more audio signals are emitted from the audio output component of the user device, reflect off a target, and are received back at the audio input component of the device. Based on the reflections, a determination is made as to whether the target is comprised of a three-dimensional face-like structure and/or face-like tissue. Using at least this determination, a finding is made as to whether the target is likely to be spoofed, rather than a legitimate, live person.
1. A computer-implemented method comprising:
emitting, using an audio output component of a user device, one or more audio signals;
receiving, using an audio input component of the user device, one or more reflections of the audio signals off a target;
determining, based on the one or more reflections, whether the target comprises at least one of a face-like structure and face-like tissue;
receiving a plurality of images of the target;
identifying, based on the images, whether the target has a first pulse;
measuring a second pulse of the target through physical contact with the target; and
determining whether the target is a spoof based at least in part on (i) the determination of whether the target comprises at least one of a face-like structure and face-like tissue, (ii) the identification of whether the target has a pulse, and (iii) the measurement of the second pulse.
2. The method of claim 1 , wherein the user device is a mobile device comprising a smartphone, a tablet, or a laptop.
3. The method of claim 1 , wherein the one or more audio signals comprise short coded pulse pings, short term chirps, or CTFM pings.
4. The method of claim 1 , further comprising:
training a classifier to identify physical features of the target; and
providing, as input to the classifier, information based on the one or more reflections of the audio signals off the target,
wherein the determination of whether the target is a spoof is further based at least in part on an output of the classifier received in response to the provided input.
5. The method of claim 1 , further comprising randomizing one or more characteristics of the one or more audio signals.
6. The method of claim 1 , further comprising:
receiving a plurality of images of the target; and
determining, based on detected light reflections in the images, whether the target comprises a three-dimensional face-like structure.
7. The method of claim 1 , wherein the first pulse is identified using remote photoplethysmography.
8. The method of claim 1 , further comprising determining whether the second pulse correlates to the first pulse, wherein the determination of whether the target is a spoof is further based at least in part on the correlation.
9. The method of claim 1 , wherein measuring the second pulse comprises receiving information associated with the second pulse from the user device or another handheld or wearable device.
10. The method of claim 9 , wherein the information associated with the second pulse comprises a ballistocardiographic signal.
11. A system comprising:
at least one memory for storing computer-executable instructions;
at least one processing unit for executing the instructions stored on the memory, wherein execution of the instructions programs the at least one processing unit to perform operations comprising:
emitting, using an audio output component of a user device, one or more audio signals;
receiving, using an audio input component of the user device, one or more reflections of the audio signals off a target;
determining, based on the one or more reflections, whether the target comprises at least one of a face-like structure and face-like tissue;
receiving a plurality of images of the target;
identifying, based on the images, whether the target has a first pulse;
measuring a second pulse of the target through physical contact with the target; and
determining whether the target is a spoof based at least in part on (i) the determination of whether the target comprises at least one of a face-like structure and face-like tissue, (ii) the identification of whether the target has a pulse, and (iii) the measurement of the second pulse.
12. The system of claim 11 , wherein the user device is a mobile device comprising a smartphone, a tablet, or a laptop.
13. The system of claim 11 , wherein the one or more audio signals comprise short coded pulse pings, short term chirps, or CTFM pings.
14. The system of claim 11 , wherein the operations further comprise:
training a classifier to identify physical features of the target; and
providing, as input to the classifier, information based on the one or more reflections of the audio signals off the target,
wherein the determination of whether the target is a spoof is further based at least in part on an output of the classifier received in response to the provided input.
15. The system of claim 11 , wherein the operations further comprise randomizing one or more characteristics of the one or more audio signals.
16. The system of claim 11 , wherein the operations further comprise:
receiving a plurality of images of the target; and
determining, based on detected light reflections in the images, whether the target comprises a three-dimensional face-like structure.
17. The system of claim 11 , wherein the first pulse is identified using remote photoplethysmography.
18. The system of claim 11 , wherein the operations further comprise determining whether the second pulse correlates to the first pulse, wherein the determination of whether the target is a spoof is further based at least in part on the correlation.
19. The system of claim 11 , wherein measuring the second pulse comprises receiving information associated with the second pulse from the user device or another handheld or wearable device.
20. The system of claim 19 , wherein the information associated with the second pulse comprises a ballistocardiographic signal.
21. A non-transitory computer-readable medium having instructions stored thereon that, when executed, program at least one processor to perform operations comprising:
emitting, using an audio output component of a user device, one or more audio signals;
receiving, using an audio input component of the user device, one or more reflections of the audio signals off a target;
determining, based on the one or more reflections, whether the target comprises at least one of a face-like structure and face-like tissue;
receiving a plurality of images of the target;
identifying, based on the images, whether the target has a first pulse;
measuring a second pulse of the target through physical contact with the target; and
determining whether the target is a spoof based at least in part on (i) the determination of whether the target comprises at least one of a face-like structure and face-like tissue, (ii) the identification of whether the target has a pulse, and (iii) the measurement of the second pulse.