Reflexive response-based video authentication method and system
A remote signal-based method and system of performing an authentication of video of a person in order to authorize access to a secured resource. The system and method are configured to cause a visual and/or audio pattern to be displayed in a remote computing device while collecting image data from the same device. The image data is evaluated to determine whether the appropriate response from the person is present. If the response is present, the system determines the image is authentic and can verify an identity of the person, and can further be configured to automatically grant the person access to one or more services, features, or information for which he or she is authorized.
1. A computer-implemented method of verifying an authenticity of video in order to protect user resources, the method comprising:
receiving, at a cloud-based authentication system and from a first computing device, a request to access a secured resource of a first user;
accessing, in response to the request, a first visual pattern from a pattern repository of the authentication system, the first visual pattern being associated with a first reflexive response pattern that should be elicited on a person's face when the person views a rendering of the first visual pattern on a display;
transmitting, from the authentication system and in response to the request, a first control signal and a second control signal to the first computing device, the first control signal including the first visual pattern and the second control signal including an audio pattern;
obtaining, at the authentication system:
first image data captured by a camera of the first computing device while presentation of the first visual pattern via the first computing device was to have occurred, the first image data including a video recording of a face of a person, and
a first response from the first user after playback of the audio pattern via the first computing device was to have occurred, the first response including a description of the directionality of the audio pattern;
determining, at the authentication system, that:
the first image data includes a second reflexive response pattern that is sufficiently similar to the first reflexive response pattern so as to be classified as a match, and
the first response is correct;
verifying, in response to the patterns matching and the first response being correct, an authenticity of the video; and
thereby granting the first user access to the secured resource for which the first user is authorized.
2. The method of claim 1 , further comprising transmitting, from the authentication system and to the first computing device, a second control signal including instructions to capture image data while the first visual pattern is displayed at the first computing device.
3. The method of claim 1 , further comprising:
receiving, at the authentication system and from a second computing device, a request to access the secured resource of the first user;
transmitting, from the authentication system and in response to the request, a second control signal to the second computing device, the second control signal including the first visual pattern;
obtaining, at the authentication system, second image data captured by a camera of the second computing device while presentation of the first visual pattern via the second computing device was to have occurred, the second image data including a video recording of a face of a person;
determining, at the authentication system, that the second image data fails to include the second reflexive response pattern;
determining, in response to the second image data failing to include the second reflexive response pattern, that there is a high likelihood of the request originating from a fraudulent source; and
denying the request and blocking access to the secured resource.
4. The method of claim 1 , wherein the first visual pattern comprises one or more graphic icons that are presented at different locations on the display.
5. The method of claim 4 , wherein the one or more graphic icons are each presented for 1-2 seconds on the display.
6. The method of claim 1 , wherein the visual pattern comprises two or more graphic icons that are presented sequentially.
7. The method of claim 1 , wherein playback of the audio pattern is from one of either a left or right speaker.
8. The method of claim 1 , wherein the secured resource includes one of a service, feature, and information for which access is restricted to one or more authorized persons.
9. The method of claim 1 , wherein the first image data is obtained during a telephone or videoconferencing session between the first user and a service representative associated with the secured resource.
10. The method of claim 1 ,
wherein the first image data is at least partially generated using deep fake technology.
11. A system for verifying an authenticity of images in order to protect user resources, the system comprising a processor and machine-readable media including instructions which, when executed by the processor, cause the processor to:
receive, at a cloud-based authentication system and from a first computing device, a request to access a secured resource of a first user;
access, in response to the request, a first visual pattern from a pattern repository of the authentication system, the first visual pattern being associated with a first reflexive response pattern that should be elicited on a person's face when the person views a rendering of the first visual pattern on a display;
transmit, from the authentication system and in response to the request, a first control signal and a second control signal to the first computing device, the first control signal including the first visual pattern and the second control signal including an audio pattern;
obtain, at the authentication system:
first image data captured by a camera of the first computing device while presentation of the first visual pattern via the first computing device was to have occurred, the first image data including a video recording of a face of a person, and
a first response from the first user after playback of the audio pattern via the first computing device was to have occurred, the first response including a description of the directionality of the audio pattern;
determining, at the authentication system, that:
the first image data includes a second reflexive response pattern that is sufficiently similar to the first reflexive response pattern so as to be classified as a match, and
the first response is correct;
verify, in response to the patterns matching and the first response being correct, an authenticity of the video; and
thereby grant first user access to the secured resource for which the first user is authorized.
12. The system of claim 11 , wherein the instructions further cause the processor to transmit, from the authentication system and to the first computing device, a second control signal including instructions to capture image data while the first visual pattern is displayed at the first computing device.
13. The system of claim 11 , wherein the first visual pattern comprises one or more graphic icons that are presented at different locations on the display.
14. The system of claim 11 , wherein the visual pattern comprises two or more graphic icons that are presented sequentially.
15. The system of claim 11 , wherein the one or more graphic icons are each presented for 1-2 seconds on the display.
16. The system of claim 11 , wherein playback of the audio pattern is from one of either a left or right speaker.
17. The system of claim 11 , wherein the secured resource includes one of a service, feature, and information for which access is restricted to one or more authorized persons.
18. The system of claim 11 , wherein the first image data is obtained during a telephone or videoconferencing session between the first user and a service representative associated with the secured resource.
19. The system of claim 11 , wherein the instructions further cause the processor to:
receive, at the authentication system and from a second computing device, a request to access the secured resource of the first user;
transmit, from the authentication system and in response to the request, a second control signal to the second computing device, the second control signal including the first visual pattern;
obtain, at the authentication system, second image data captured by a camera of the second computing device while presentation of the first visual pattern via the second computing device was to have occurred, the second image data including a video recording of a face of a person;
determine, at the authentication system, that the second image data fails to include the second reflexive response pattern;
determine, in response to the second image data failing to include the second reflexive response pattern, that there is a high likelihood of the request originating from a fraudulent source; and
deny the request and block access to the secured resource.
20. The system of claim 19 , wherein the first image data is at least partially generated using deep fake technology.