Granted Patent B2

US 12,314,359 · App. 17/457,297 · Granted May 27, 2025

Inventors: Jeffrey Carlyle Wieker (Falls Church, VA); Clayton Johnson (Edgewood, MD)

Assignee: Capital One Services, LLC

G06F21/316

Abstract

Claims (66)

1. A system for dynamic authentication of a user on a mobile device, the system comprising:

one or more memories; and

one or more processors, communicatively coupled to the one or more memories, configured to:

receive, from one or more sensors of the mobile device, measurements associated with

a grip on the mobile device;

receive, from an operating system of the mobile device, an indicator of one or more properties associated with the mobile device, wherein the one or more properties include

whether the mobile device is rooted or jailbroken;

receive, from an application of the mobile device, a record of one or more interactions with the application by the user of the mobile device;

input the measurements, the indicator of the one or more properties, and the record to a model that determines a score associated with a security level for the user,

wherein determining the score is, at least in part, based on a difference between a numerical indicator associated with the grip and a numerical indicator associated with historical grips satisfying a threshold;

apply one or more rules to the score to determine one or more prompts to authenticate the user, wherein determining the one or more prompts comprises:

determining, based on the score, a type of prompt to generate, and

determining, based on the score, a quantity of prompts to generate;

present, while the user is viewing a screen associated with the application, the one or more prompts; and

authenticate the user, based on one or more responses to the one or more prompts, to allow the user to continue viewing the screen.

2. The system of claim 1 , wherein the model is stored and applied at the operating system of the mobile device.

3. The system of claim 1 , wherein the model is stored and applied at the application of the mobile device.

4. The system of claim 1 , wherein the one or more sensors comprise an accelerometer, a compass, a gyroscope, an optical sensor, or a combination thereof.

5. The system of claim 1 , wherein the one or more interactions comprise a login technique used by the user, a history of menus accessed by the user, and a time associated with viewing a screen of the application.

6. The system of claim 1 , wherein the one or more processors, to present the one or more prompts, are configured to:

obscure at least part of the screen that the user is viewing, or

freeze one or more applications executing on the operating system.

7. The system of claim 1 , wherein the one or more processors are further configured to:

terminate the application when at least one of the one or more responses are classified as incorrect, and

cause the application to require the user to contact customer support before attempting to access the application again.

8. The system of claim 1 , wherein the measurements include measurements associated with a location of the mobile device, and

wherein the score is, at least in part, determined based on a distance between the location and a historical location satisfying a threshold.

9. A method of dynamically authenticating a user on a mobile device, comprising:

receiving, from a first sensor of the mobile device, measurements indicating a location of the mobile device;

receiving, from a second sensor of the mobile device, measurements associated with a grip of the user on the mobile device;

receiving, from an operating system of the mobile device, an indicator of one or more properties associated with the mobile device, wherein the one or more properties include an indication of whether the mobile device is rooted or jailbroken;

inputting the indicator of the one or more properties associated with the mobile device and an indicator of the location and an indicator of the grip to a model that outputs an indication associated with suspicious activity,

wherein outputting the indication is, at least in part, based on a difference between a numerical indicator associated with the grip and a numerical indicator associated with historical grips satisfying a threshold;

applying one or more rules to the indication to determine a type and a quantity of one or more prompts to authenticate the user;

presenting, while the user is viewing a screen associated with an application using the model, the one or more prompts; and

determining whether to allow the user to continue viewing the screen based on one or more responses to the one or more prompts.

10. The method of claim 9 , further comprising:

receiving, from the first sensor of the mobile device, updated measurements indicating an updated location of the mobile device;

receiving, from the second sensor of the mobile device, updated measurements associated with an updated grip of the user on the mobile device;

inputting indicators of the updated location and the updated grip to the model, wherein the model outputs an updated indication associated with suspicious activity; and

determining to allow the user to continue viewing an updated screen based on the updated indication.

11. The method of claim 9 , wherein determining whether to allow the user to continue viewing the screen comprises:

terminating the application when the one or more responses are classified as incorrect.

12. The method of claim 9 , wherein determining whether to allow the user to continue viewing the screen comprises:

locking the screen when the one or more responses are classified as incorrect.

13. The method of claim 9 , wherein the model is stored on a memory of the mobile device.

14. A non-transitory computer-readable medium storing a set of instructions for dynamically authenticating a user on a mobile device, the set of instructions comprising:

one or more instructions that, when executed by one or more processors of a device, cause the device to:

receive, from one or more sensors of the mobile device, measurements indicating a location of the mobile device and measurements associated with a grip of the user on the mobile device;

determine, at an operating system of the mobile device, an indicator of one or more

properties associated with the mobile device, wherein the one or more properties include

whether the mobile device is rooted or jail broken

input the measurements and the indicator of the one or more properties to a model that outputs a determination of whether the grip, the location, and the one or more properties are consistent with a profile of the user,

wherein outputting the determination is, at least in part, based on a difference between a numerical indicator associated with the grip and a numerical indicator associated with historical grips satisfying a threshold;

apply one or more rules to the output from the model to determine a type and a quantity of one or more prompts to authenticate the user;

present, while the user is viewing a screen associated with the operating system, the one or more prompts; and

authenticate the user, based on one or more responses to the one or more prompts, to allow the user to continue viewing the screen.

15. The non-transitory computer-readable medium of claim 14 , wherein the one or more prompts comprise a biometric prompt, a password-based prompt, a two-factor prompt, or a combination thereof.

16. The non-transitory computer-readable medium of claim 14 , wherein the model is a machine learning model based on historical data associated with the user.

17. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, when executed by the one or more processors, further cause the device to:

update the model based on the one or more responses.

18. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, that cause the device to present the one or more prompts, cause the device to:

obscure at least part of the screen that the user is viewing.

19. The non-transitory computer-readable medium of claim 14 , wherein the one or more instructions, that cause the device to present the one or more prompts, cause the device to:

freeze one or more applications executing on the operating system.

20. The non-transitory computer-readable medium of claim 14 , wherein outputting the determination is, at least in part, based on a distance between the location and a historical location satisfying a threshold.

Assignments (1)

Continuity (1)

References Cited (12)