Verification request authentication machine
A device authenticates a request to verify a user. The device accesses a face image that depicts a face of the person and includes a characteristic noise pattern inserted by a camera of the device. The device also accesses a geolocation at which the device captured the face image and inputs the face image and the geolocation into an artificial intelligence engine that outputs a face score, a device score, and a location score. The device next submits the request with the scores to a server machine and obtains an authentication score from the server machine. The device then presents an indication that the request to verify the person is authentic based on a comparison of the obtained authentication score to a threshold authentication score.
1. A method comprising:
providing, by one or more processors, an image to an artificial intelligence engine, the image depicting a face of a user to be verified and including a characteristic noise pattern of a camera that captured the image, the artificial intelligence engine being trained to generate a face score based on the image and generate a camera score based on the characteristic noise pattern;
obtaining, by the one or more processors, an authentication score based on the face score and the camera score, the authentication score corresponding to a request to verify the user; and
causing, by the one or more processors, presentation of an indication that the request to verify the user is authentic based on a comparison of the authentication score to a threshold score.
2. The method of claim 1 , further comprising:
providing location data to the artificial intelligence engine, the location data indicating a location at which the camera captured the image, the camera being included in a device; and wherein:
the artificial intelligence engine is trained to generate a location score based on the location data that indicates the location at which the camera included in the device captured the image; and
the obtaining of the authentication score that corresponds to the request to verify the user is based on the location score, the face score, and the camera score.
3. The method of claim 2 , further comprising:
accessing the image from the camera that captured the image; and
in response to the accessing of the image from the camera, accessing the location data from a location sensor included in the device.
4. The method of claim 2 , further comprising:
accessing the image from an image library stored by the device; and
in response to the accessing of the image from the image library, accessing the location data from metadata of the image.
5. The method of claim 2 , further comprising:
accessing accelerometer data that indicates a movement of the camera during capture of the image; and wherein:
the artificial intelligence engine is trained to generate the camera score based on the accelerometer data.
6. The method of claim 2 , wherein:
the artificial intelligence engine is trained to generate the location score based on the location at which the camera captured the image and a background analysis of the image.
7. The method of claim 2 , wherein:
the artificial intelligence engine is trained to generate the location score based on the location at which the camera captured the image and a metadata analysis of the image.
8. The method of claim 1 , wherein:
the characteristic noise pattern of the camera indicates a set of one or more manufacturing deviations that occurred during manufacture of the camera.
9. The method of claim 1 , wherein:
the artificial intelligence engine trained to generate the face score and the camera score includes one or more of a deep neural network, a convolutional neural network, or a recurrent neural network.
10. The method of claim 1 , wherein:
the obtaining of the authentication score includes causing the face score and the camera score to be inputted into a neural network and obtaining the authentication score output therefrom.
11. The method of claim 1 , wherein:
the artificial intelligence engine is trained to generate the face score based on a liveness analysis of the image.
12. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
providing an image to an artificial intelligence engine, the image depicting a face of a user to be verified and including a characteristic noise pattern of a camera that captured the image, the artificial intelligence engine being trained to generate a face score based on the image and generate a camera score based on the characteristic noise pattern;
obtaining an authentication score based on the face score and the camera score, the authentication score corresponding to a request to verify the user; and
causing presentation of an indication that the request to verify the user is authentic based on a comparison of the authentication score to a threshold score.
13. The non-transitory machine-readable storage medium of claim 12 , wherein the operations further comprise:
providing location data to the artificial intelligence engine, the location data indicating a location at which the camera captured the image, the camera being included in a device; and wherein:
the artificial intelligence engine is trained to generate a location score based on the location data that indicates the location at which the camera included in the device captured the image; and
the obtaining of the authentication score that corresponds to the request to verify the user is based on the location score, the face score, and the camera score.
14. The non-transitory machine-readable storage medium of claim 13 , wherein the operations further comprise:
accessing accelerometer data that indicates a movement of the camera during capture of the image; and wherein:
the artificial intelligence engine is trained to generate the camera score based on the accelerometer data.
15. The non-transitory machine-readable storage medium of claim 12 , wherein:
the characteristic noise pattern of the camera indicates a set of one or more manufacturing deviations that occurred during manufacture of the camera.
16. A system comprising:
one or more processors; and
a memory storing instructions that, when executed by at least one processor among the one or more processors, cause the system to perform operations comprising:
providing an image to an artificial intelligence engine, the image depicting a face of a user to be verified and including a characteristic noise pattern of a camera that captured the image, the artificial intelligence engine being trained to generate a face score based on the image and generate a camera score based on the characteristic noise pattern;
obtaining an authentication score based on the face score and the camera score, the authentication score corresponding to a request to verify the user; and
causing presentation of an indication that the request to verify the user is authentic based on a comparison of the authentication score to a threshold score.
17. The system of claim 16 , wherein the operations further comprise:
providing location data to the artificial intelligence engine, the location data indicating a location at which the camera captured the image, the camera being included in a device; and wherein:
the artificial intelligence engine is trained to generate a location score based on the location data that indicates the location at which the camera included in the device captured the image; and
the obtaining of the authentication score that corresponds to the request to verify the user is based on the location score, the face score, and the camera score.
18. The system of claim 17 , wherein the operations further comprise:
accessing accelerometer data that indicates a movement of the camera during capture of the image; and wherein:
the artificial intelligence engine is trained to generate the camera score based on the accelerometer data.
19. The system of claim 17 , wherein:
the artificial intelligence engine is trained to generate the location score based on the location at which the camera captured the image and a background analysis of the image.
20. The system of claim 16 , wherein:
the obtaining of the authentication score includes causing the face score and the camera score to be inputted into a neural network and obtaining the authentication score output therefrom.