UNOBTRUSIVE VERIFICATION OF USER IDENTITY

• US 20150261944A1
• Filed: 08/04/2014
• Published: 09/17/2015
• Est. Priority Date: 03/17/2014
• Status: Active Grant

• Current Assignee: Sensory Incorporated
• Original Assignee: Sensory Incorporated
• Inventors: Hosom, John-Paul, Mozer, Todd F., Vermeulen, Pieter J., Pellom, Bryan L.
• Granted Patent: US 10,248,770 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 2221/2111 Location-sensitive, e.g. geographical location, GPS
• CPC Class Codes: G06F 2221/2117 User registration

Abstract

Techniques for unobtrusively verifying the identity of a user of a computing device are provided. In one embodiment, the computing device can establish one or more verification models for verifying the user'"'"'s identity, where at least a subset of the one or more verification models is based on enrollment data that is collected in an unobtrusive manner from the user. The computing device can then verify the user'"'"'s identity using the one or more verification models.

Claims

1. A method comprising:

establishing, by a computing device, one or more verification models for verifying an identity of a user, wherein at least a subset of the one or more verification models is based on enrollment data that is collected in an unobtrusive manner from the user; and

verifying, by the computing device, the identity of the user using the one or more verification models.

2. The method of claim 1 wherein the verifying is performed on a continuous basis while the user is interacting with the computing device.

3. The method of claim 1 wherein the verifying is also performed in a manner that is unobtrusive to the user.

4. The method of claim 1 wherein the one or more verification models include a first verification model that is created via an initial enrollment procedure.

5. The method of claim 4 wherein the initial enrollment procedure is carried out explicitly or implicitly.

6. The method of claim 4 wherein the first verification model is updated on a periodic basis using enrollment data that is collected unobtrusively from the user.

7. The method of claim 4 wherein the one or more verification models further include a second verification model that is different from the first verification model, and wherein the second verification model is created and updated using enrollment data that is collected unobtrusively from the user.

8. The method of claim 7 wherein the first and second verification models operate on different types of data streams for verifying the identity of the user.

9. The method of claim 8 wherein the different types of data streams include acoustic data, visual data, location data, and motion data.

10. The method of claim 7 wherein the first and second verification models are selected from a group consisting of:

a voice-based verification model, a face-based verification model, a location-based verification model, a motion-based verification model, a retina-based verification model, a fingerprint-based verification model, and a handprint-based verification model.

11. The method of claim 7 wherein the enrollment data used to create and update the second verification model corresponds to data that is determined to be correlated with the user.

12. The method of claim 11 wherein the enrollment data used to create the second verification model corresponds to data collected while the user is involved in the initial enrollment procedure.

13. The method of claim 1 wherein verifying the identity of the user using the one or more verification models comprises:

identifying one or more data streams that are available for verifying the identity of the user, without requiring specific verification input from the user; and

applying the one or more data streams to the one or more verification models; and

generating, based on the applying, a verification score.

14. The method of claim 13 wherein generating the verification score comprises:

combining output from the one or more verification models.

15. The method of claim 14 wherein combining output from the one or more verification models comprises:

assigning a weight to the output of each verification model based one or more criteria.

16. The method of claim 13 wherein verifying the identity of the user using the one or more verification models further comprises:

determining whether the verification score meets or exceeds a predefined threshold; and

if the verification score does not meet or exceed the predefined threshold, asking the user to provide explicit verification input.

17. The method of claim 16 wherein the predefined threshold is associated with an application or task that the user is attempting to run or perform.

18. A non-transitory computer readable medium having stored thereon program code executable by a processor of a computing device, the program code comprising:

code that causes the processor to establish one or more verification models for verifying an identity of a user of the computing device, wherein at least a subset of the one or more verification models is based on enrollment data that is collected in an unobtrusive manner from the user; and

code that causes the processor to verify the identity of the user using the one or more verification models.

19. A computing device comprising:

a processor; and

a non-transitory computer readable medium having stored thereon executable program code which, when executed by the processor, causes the processor to;

establish one or more verification models for verifying an identity of a user of the computing device, wherein at least a subset of the one or more verification models is based on enrollment data that is collected in an unobtrusive manner from the user; and

verify the identity of the user using the one or more verification models.