Spoof detection using optokinetic response

1. A method for preventing access to a secure system based on determining a captured video to be an alternative representation of a live person, the method comprising:

determining a first stimulus velocity at which to present a stimulus to a subject on a user: interface of a device, wherein the first stimulus velocity is based on a viewing distance between the subject and the user-interface being a first distance;

presenting the stimulus to the subject at the first stimulus velocity on the user-interface of the device;

determining that the viewing distance between the subject and the user-interface has changed from the first distance to a second distance;

selecting a second stimulus velocity based on the second distance;

presenting the stimulus at the second stimulus velocity on the user-interface;

capturing video of the subject while the subject is within a field of view of a video capture device after presentation of the stimulus at the second stimulus velocity;

analyzing the video to extract ocular data comprising a response of the subject to the stimulus when presented at the second stimulus velocity;

determining, by comparing the ocular data to one or more reference patterns that the subject in the captured video is an alternative representation of a live person, wherein the one or more reference patterns are selected based on the second stimulus velocity; and

responsive to determining that the subject in the captured video is an alternative representation of a live person, preventing access to a secured system.

2. The method of claim 1 , further comprising:

capturing a second video of a second subject after a second presentation of the stimulus, to the second subject, at the second stimulus velocity;

analyzing the second video to extract a second set of ocular data comprising a response of the second subject to the stimulus;

determining, by comparing the second set of ocular data to the one or more reference patterns, that the second subject is a live person; and

responsive to determining that the second subject is a live person, initiating an authentication process for determining if the live person is authorized to access the secured system.

3. The method of claim 1 , further comprising selecting a type of stimulus to present from among multiple types of stimulus.

4. The method of claim 1 , wherein the stimulus is a high contrast stimulus.

5. The method of claim 1 , wherein analyzing the captured video comprises tracking eye movements after presentation of the stimulus.

6. The method of claim 5 , wherein the reference patterns include a first pattern corresponding to optokinetic nystagmus.

7. The method of claim 6 , wherein comparing the ocular data comprises comparing the tracked eye movements to the first pattern corresponding to optokinetic nystagmus.

8. The method of claim 1 , wherein analyzing the captured video comprises tracking changes in pupillary dynamics after presentation of the stimulus.

9. The method of claim 8 , wherein the reference patterns include a second pattern corresponding to an expected change in pupillary dynamics.

10. The method of claim 9 , wherein comparing the ocular data comprises comparing the tracked changed in pupillary dynamics to the second pattern corresponding to the expected change in pupillary dynamics.

11. A system comprising:

a video acquisition device configured to capture a video of a subject who is within a field of view of a video capture device;

a processing device configured to:

determine a first stimulus velocity at which to present a stimulus to a subject on a user: interface of a device, wherein the first stimulus velocity is based on a viewing distance between the subject and the user-interface being a first distance;

present the stimulus to the subject at the first stimulus velocity;

determine that the viewing distance between the subject and the user-interface has changed from the first distance to a second distance,

select a second stimulus velocity based on the second distance, and

present the stimulus at the second stimulus velocity on the user-interface; and

a video analysis engine comprising one or more processing devices, the video analysis engine configured to:

analyze video of the subject captured by the video acquisition device while the subject is within a field of view of the video capture device after presentation of the stimulus at the second stimulus velocity, to extract ocular data comprising a response of the subject to the stimulus when presented at the second stimulus velocity;

determine, by comparing the ocular data to one or more reference patterns that the subject in the captured video is an alternative representation of a live person, wherein the one or more reference patterns are selected based on the second stimulus velocity; and

responsive to determining that the subject in the captured video is an alternative representation of a live person, prevent access to a secured system.

12. The system of claim 11 :

wherein the video acquisition device is configured to capture a second video of a second subject after a second presentation of the stimulus, to the second subject, at the second stimulus velocity; and

wherein the video analysis engine is configured to:

analyze the second video to extract a second set of ocular data comprising a response of the second subject to the stimulus;

determine, by comparing the second set of ocular data to the one or more reference patterns, that the second subject is a live person; and

responsive to determining that the second subject is a live person, initiate an authentication process for determining if the live person is authorized to access the secured system.

13. The system of claim 11 , wherein the stimulus is a high contrast stimulus.

14. The system of claim 11 , wherein analyzing the captured video comprises tracking eye movements after presentation of the stimulus.

15. One or more machine-readable non-transitory storage devices comprising machine-readable instructions configured to cause one or more processing devices to execute operations comprising:

determining a first stimulus velocity at which to present a stimulus to a subject on a user: interface of a device, wherein the first stimulus velocity is based on a viewing distance between the subject and the user-interface being a first distance;

presenting the stimulus to the subject at the first stimulus velocity on the user-interface of the device;

determining that the viewing distance between the subject and the user-interface has changed from the first distance to a second distance;

selecting a second stimulus velocity based on the second distance;

presenting the stimulus at the second stimulus velocity on the user-interface;

capturing video of the subject while the subject is within a field of view of a video capture device after presentation of the stimulus at the second stimulus velocity;

analyzing the video to extract ocular data comprising a response of the subject to the stimulus when presented at the second stimulus velocity;

determining, by comparing the ocular data to one or more reference patterns that the subject in the captured video is an alternative representation of a live person, wherein the one or more reference patterns are selected based on the second stimulus velocity; and

responsive to determining that the subject in the captured video is an alternative representation of a live person, preventing access to a secured system.

16. The machine-readable storage devices of claim 15 , the operations further comprising:

capturing a second video of a second subject after a second presentation of the stimulus, to the second subject, at the second stimulus velocity;

analyzing the second video to extract a second set of ocular data comprising a response of the second subject to the stimulus;

determining, by comparing the second set of ocular data to the one or more reference patterns, that the second subject is a live person; and

responsive to determining that the second subject is a live person, initiating an authentication process for determining if the live person is authorized to access the secured system.

17. The machine-readable storage devices of claim 15 , the operations further comprising selecting a type of stimulus to present from among multiple types of stimulus.