User verification systems and methods
This disclosure relates to systems and methods for verifying the presentation of content to a target audience using generated metrics indicative of a likelihood that the content was presented to actual human individuals within the target audience. In some instances, such a metric may be associated with a probability model estimating that a user (e.g., a user of a device) is human and not a bot and/or other automated service. Metrics consistent with aspects of the disclosed embodiments may be generated based, at least in part, on user information received from a user and/or associated devices and/or associated services. Consistent with various disclosed embodiments, metrics indicative of whether a user is human, content distribution decisions and user agency decisions may use such metrics.
1. A method performed by a user authentication system comprising a processor and a non-transitory computer readable storage medium storing instructions that, when executed by the processor, cause the user authentication system to perform the method, the method comprising:
receiving a plurality of messages from a first device, wherein possession of the plurality of messages provides an indication of a relative likelihood that a user of the first device is a human user, the plurality of messages comprising:
at least a first message originating from a second device and being received by the first device from the second device based on the first device being located within a threshold proximity of the second device, the second device being a different device than the first device, the at least a first message being signed using a private key associated with the second device;
at least a second message originating from a third device and being received by the first device from the third device based on the first device being located within a threshold proximity of the third device, the third device being a different device than the first device and the second device, the at least a second message being signed using a private key associated with the third device;
generating, based on the plurality of messages received from the first device, a Turing score associated with the user of the first device, the Turing score indicating the relative likelihood that the user of the first device is a human user;
receiving a request from the user of the first device to authenticate access to a service;
accessing a parameter specifying a threshold Turing score associated with access to the service;
determining that the generated Turing score associated with the user satisfies the threshold Turing score specified in the parameter; and
authenticating access to the service based at least in part on the determination.
2. The method of claim 1 , wherein the private key associated with the second device comprises a private device key of the second device and the private key associated with the third device comprises a private device key of the third device.
3. The method of claim 2 , wherein the private device key associated with the second device comprises a private device key unique to the second device and the private device key associated with the third device comprises a private device key unique to the third device.
4. The method of claim 1 , wherein the service comprises a content service.
5. The method of claim 4 , wherein the content service comprises a content publishing service.
6. The method of claim 1 , wherein the method further comprises receiving one or more signals from the first device.
7. The method of claim 6 , wherein the one or more signals comprise at least one user input provided by the user to the first device and wherein generating the Turing score is further based on the one or more signals.
8. The method of claim 7 , wherein the one or more signals comprise information generated based on the user's response to an interactive query presented to the user on the first device.
9. The method of claim 6 , wherein the one or more signals comprise information generated by monitoring a user's interaction with the first device and wherein generating the Turing score is further based on the one or more signals.
10. The method of claim 1 , wherein generating the Turing score comprises comparing the plurality of messages to panel data to identify a relative deviation of the received plurality of messages from the panel data.
11. The method of claim 1 , wherein generating the Turing score comprises comparing the plurality of messages to prior user data.
12. The method of claim 11 , wherein the prior user data comprises prior verified user data.
13. The method of claim 1 , wherein possession of the plurality of messages by the first device provides a digital fingerprint associated with the user of the first device.
14. The method of claim 1 , wherein the method further comprises verifying one or more signatures associated with each message of the plurality of messages.
15. The method of claim 1 , wherein each message of the plurality of messages comprises one or more of timestamp information, location information, and observation information.