Unobtrusive verification of user identity

• US 10,248,770 B2
• Filed: 08/04/2014
• Issued: 04/02/2019
• 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.
• Primary Examiner(s): Rashid, Harunur
• Application Number:
  US14/450,528
• Publication Number:
  US 20150261944A1
• Time in Patent Office: 1,702 Days
• 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:

creating, by a computing device, a first verification model for a user, the first verification model being based upon enrollment data that is collected via an explicit enrollment procedure and including a first set of biometric data for verifying an identity of the user;

verifying, by the computing device, the identity of the user a first time using the first verification model;

unobtrusively collecting, by the computing device, one or more reliable data streams associated with the user, wherein the one or more reliable data streams are collected while the identity of the user is verified the first time using the first verification model;

unobtrusively creating, by the computing device, a second verification model for the user, wherein the second verification model is based upon the one or more reliable data streams that are collected while the identity of the user is verified the first time using the first verification model, wherein the second verification model includes a second set of biometric data for verifying the identity of the user, and wherein the second set of biometric data included in the second verification model comprises biometric data of a different type than the first set of biometric data included in the first verification model;

unobtrusively collecting, by the computing device, one or more verification data streams from the user, the one or more verification data streams being separate from the enrollment data used to create the first verification model, and the one or more reliable data streams used to create the second verification model; and

verifying, by the computing device, the identity of the user a second time by applying the one or more verification data streams to the first and second verification models, wherein verifying the identity of the user the second time comprises;

receiving, by the computing device, a first verification result generated by a server remote from the computing device, the first verification result being generated by the server based on instances of the first and second verification models stored on the server;

comparing, by the computing device, the first verification result with a second verification result generated by the computing device based on instances of the first and second verification models stored on the computing device; and

if the first verification result generated by the server is consistent with the second verification result generated by the computing device, authorizing the user to perform a secured action on the computing device.

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

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

4. The method of claim 1 wherein the first and second verification models are unobtrusively updated on a periodic basis based upon additional reliable data streams that are identified during the computing device'"'"'s runtime operation.

5. The method of claim 1 wherein the different types of user verification data include acoustic data, visual data, location data, and motion data.

6. The method of claim 1 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.

7. The method of claim 1 wherein verifying the identity of the user the second time by applying the one or more verification data streams to the first and second verification models further comprises:

generating, based on the applying, a verification score.

8. The method of claim 7 wherein generating the verification score comprises:

combining output from the first and second verification models.

9. The method of claim 8 wherein combining output from the first and second verification models comprises:

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

10. The method of claim 7 wherein verifying the identity of the user the second time by applying the one or more verification data streams to the first and second 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.

11. The method of claim 10 wherein the predefined threshold is associated with an application or task that the user is attempting to run or perform.

12. 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 create a first verification model for a user, the first verification model being based upon enrollment data that is collected via an explicit enrollment procedure and including a first set of biometric data for verifying an identity of the user;

code that causes the processor to verify the identity of the user a first time using the first verification model;

code that causes the processor to unobtrusively collect one or more reliable data streams associated with the user, wherein the one or more reliable data streams are collected while the identity of the user is verified the first time using the first verification model;

code that causes the processor to unobtrusively create a second verification model for the user, wherein the second verification model is based upon the one or more reliable data streams that are collected while the identity of the user is verified the first time using the first verification model, wherein the second verification model includes a second set of biometric data for verifying the identity of the user, and wherein the second set of biometric data included in the second verification model comprises biometric data of a different type than the first set of biometric data included in the first verification model;

code that causes the processor to unobtrusively collect one or more verification data streams from the user, the one or more verification data streams being separate from the enrollment data used to create the first verification model and the one or more reliable data streams used to create the second verification model; and

code that causes the processor to verify the identity of the user a second time by applying the one or more verification data streams to the first and second verification models wherein verifying the identity of the user the second time comprises;

receiving, by the processor, a first verification result generated by a server remote from the computing device, the first verification result being generated by the server based on instances of the first and second verification models stored on the server;

comparing, by the processor, the first verification result with a second verification result generated by the processor based on instances of the first and second verification models stored on the computing device; and

if the first verification result generated by the server is consistent with the second verification result generated by the processor, authorizing the user to perform a secured action on the computing device.

13. 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;

create a first verification model for a user, the first verification model being based upon enrollment data that is collected via an explicit enrollment procedure and including a first set of biometric data for verifying an identity of the user;

verify the identity of the user a first time using the first verification model;

unobtrusively collect one or more reliable data streams associated with the user, wherein the one or more reliable data streams are collected while the identity of the user is verified the first time using the first verification model;

unobtrusively create a second verification model for the user, wherein the second verification model is based upon the one or more reliable data streams that are collected while the identity of the user is verified the first time using the first verification model, wherein the second verification model includes a second set of biometric data for verifying the identity of the user, and wherein the second set of biometric data included in the second verification model comprises biometric data of a different type than the first set of biometric data included in the first verification model;

unobtrusively collect one or more verification data streams from the user, the one or more verification data streams being separate from the enrollment data used to create the first verification model and the one or more reliable data streams used to create the second verification model; and

verify the identity of the user a second time by applying the one or more verification data streams to the first and second verification models, wherein verifying the identity of the user the second time comprises;

receiving a first verification result generated by a server remote from the computing device, the first verification result being generated by the server based on instances of the first and second verification models stored on the server;

comparing the first verification result with a second verification result generated by the computing device based on instances of the first and second verification models stored on the computing device; and

if the first verification result generated by the server is consistent with the second verification result generated by the computing device, authorizing the user to perform a secured action on the computing device.