Systems and methods for automatically performing secondary authentication of primary authentication credentials

Patent metadata

Field	Value
Publication number	US-11290450-B2
Application number	US-202016871326-A
Country	US
Kind code	B2
Filing date	May 11, 2020
Priority date	Jun 10, 2019
Publication date	Mar 29, 2022
Grant date	Mar 29, 2022

Abstract

The disclosed technology includes systems and methods for determining secondary authentication of a user's log-in attempts by comparing received behavioral biometric data and/or received scenario-specific data to saved behavioral biometric data and/or saved scenario-specific data, respectively. Responsive to determining that the received behavioral biometric data and/or received scenario-specific data is above a predetermined threshold of similarity with respect to the saved behavioral biometric data and/or saved scenario-specific data, respectively, the systems and methods can determine that the corresponding log-in attempt is secondarily authenticated. of a user device via behavioral biometric data. Responsive to determining that the level of similarity is not above the predetermined threshold, the systems and methods can initiate a secondary authentication method and can associate the received behavioral biometric data with a second user model.

First claim

What is claimed is:

1. A method comprising:
receiving, from a user device, one or more submissions comprising (i) authentication credentials and (ii) scenario data comprising (a) device elevation data corresponding to a height of the user device relative a reference point and (b) device orientation data corresponding to a physical orientation of the user device, the scenario data being contemporaneously detected by one or more sensors of the user device along with a corresponding entry of the authentication credentials;
creating, based at least in part on the one or more submissions, one or more user models personalized to a user associated with the user device by:
determining, based at least in part on the scenario data, one or more use-poses of the user during entry of the authentication credentials, each use-pose corresponding to a full-body position of the user; and
associating each of the one or more user models with a use-pose of the user during entry of the authentication credentials;

receiving, from the user device, a current submission comprising (i) current authentication data indicative of a current entry of the authentication credentials and (ii) current scenario data comprising current device elevation data and current device orientation data;
for each of the one or more user models:
comparing the current submission to a corresponding user model of the one or more user models; and
determining a level of similarity between the current submission and the corresponding user model of the one or more user models; and

responsive to determining that the level of similarity is above a predetermined threshold, determining that the current submission meets a secondary authentication requirement.

2. The method of claim 1 further comprising, responsive to determining that at least one of each level of similarity is not above the predetermined threshold, transmitting, to the user device, a request for secondary authentication credentials.

3. The method of claim 1 further comprising:
receiving, from the user device and for each of the one or more submissions, time data indicating a time associated with an entry of the corresponding entry of the authentication credentials; and
for each user model of the one or more user models, determining a time range during which the use-pose associated with the corresponding user model is likely to be used.

4. The method of claim 1 , wherein the scenario data for each of the one or more submissions further comprises device location data indicating a geographic location of the user device during an entry of the corresponding entry of the authentication credentials, the method further comprising, for each of the one or more user models, determining a geographic area within which the use-pose associated with the corresponding user model is likely to be used.

5. The method of claim 1 , wherein the use-pose comprises at least one of a prone position, a supine position, a Fowler's position, a standing position, a seated position, a squatting position, and a hunched position.

6. The method of claim 1 , wherein the user device is a user device of a plurality of user devices, the method further comprising:
receiving, from each of the plurality of user devices, one or more submissions comprising (i) authentication credentials and (ii) scenario data comprising device elevation data and device orientation data, the scenario data being detected, by one or more sensors of the user device, contemporaneously with a corresponding entry of the authentication credentials;
determining, from the one or more submissions of the authentication credentials, one or more device-specific user models personalized to the user; and
associating each of the one or more device-specific user models with a use-pose of the user using a corresponding user device of the plurality of user devices during one or more entries of the authentication credentials.

7. The method of claim 1 , wherein the user device is a handheld mobile device.

8. The method of claim 1 , wherein the user device comprises all of the one or more sensors within a single housing.

9. The method of claim 1 , wherein the predetermined threshold is a first predetermined threshold, the method further comprising:
for each of the one or more user models:
responsive to determining that the level of similarity between the current submission and the corresponding user model of the one or more user models is below the first predetermined threshold and a second predetermined threshold:
initiating a secondary authentication method; and
updating the one or more user models with a new user model that is associated with the user device and the current scenario data.

10. A non-transitory, computer-readable medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to:
receive, from a user device, a current submission comprising (i) current authentication data indicative of a current entry of authentication credentials and (ii) current scenario data comprising (a) current device elevation data corresponding to a current height of the user device relative a reference point and (b) current device orientation data corresponding to a current physical orientation of the user device, the current scenario data being contemporaneously detected with the current entry of the authentication credentials;
determine a use-pose associated with the current scenario data, the use-pose corresponding to a full-body position of a user associated with the user device during entry of the current authentication data;
for each of one or more user models:
compare the determined use-pose to a corresponding user model of the one or more user models, each of the one or more user models being personalized to the user and being associated with a full-body position of the user during entry of the authentication credentials; and
determine a level of similarity between the determined use-pose and the corresponding user model of the one or more user models; and
responsive to determining that the level of similarity is above a predetermined threshold, determine that the current submission meets a secondary authentication requirement.

11. The non-transitory, computer-readable medium of claim 10 , wherein:
the current submission comprises current device location data indicating a geographic location of the user device during a corresponding entry of the authentication credentials, and
the instructions, when executed by the one or more processors, further cause the one or more processors to:
for each of the one or more user models, compare the current device location data to a model location data of a corresponding user model of the one or more user models;
determine a level of similarity between the current device location data and the model location data of the corresponding user model of the one or more user models; and
responsive to determining that the level of similarity is above a predetermined threshold, determine that the current submission meets a location requirement of the secondary authentication requirement.

12. The non-transitory, computer-readable medium of claim 10 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
receive, from the user device, time data indicating a time associated with the current entry of the authentication credentials; and
for each user model of the one or more user models, compare the time data to a time range during which the full-body position associated with the corresponding user model is likely to be used.

13. The non-transitory, c

Assignees

• Capital One Services Llc

Inventors

• Edwards Joshua
• Ji Jason
• Chatman Ljubica
• Mossoba Michael
• Rodriguez Carlos

Classifications

• H04L63/083

  using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226) · CPC title

• H04W12/068

  using credential vaults, e.g. password manager applications or one time password [OTP] applications · CPC title

• H04L2463/082

  applying multi-factor authentication · CPC title

• H04L63/0861 Primary

  using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231) · CPC title

• H04L63/102

  Entity profiles · CPC title