US-12625931-B2 - Computer-based systems having components configured/programmed for video password based authentication and methods of use thereof

US12625931B2US 12625931 B2US12625931 B2US 12625931B2US-12625931-B2

Abstract

Systems and methods of video password based user authentication via machine learning techniques are disclosed. In one embodiment, an exemplary computer-implemented method may comprise: receiving a request to register a video password from a first user; establishing at least one user-specific authentication criterion for the first user based on first video password data; receiving a login attempt from a second computing device associated with a second user who submits to be the first user, the login attempt comprising second video password data; utilizing a trained video password authentication machine learning model to determine a first comparison result and a second comparison result based on the first and second video password data, and accepting or rejecting the login attempt based on at least one of the first comparison result and the second comparison result.

Inventors

Lin Ni Lisa Cheng
Tyler Maiman
Joshua Edwards
Shabnam KOUSHA
Asher SMITH-ROSE

Assignees

CAPITAL ONE SERVICES, LLC

Dates

Publication Date: 20260512
Application Date: 20240715

Claims (20)

1 . A method comprising: obtaining, by one or more processors, current visual input data that comprises: motion data that matches baseline motion data, and non-motion data that differs from the baseline motion data based on at least one authentication criterion; receiving, by the one or more processors, a request to register a password of a first user from a first computing device, the request comprising first password data associated with the first user; establishing, by the one or more processors, at least one user-specific authentication criterion for the first user based on: the first password data, and the current visual input data; and registering, by the one or more processors, the password of the first user in association with the at least one user-specific authentication criterion.
2 . The method of claim 1 , further comprising: receiving a login attempt from a second computing device associated with a second user, the login attempt comprising second password data associated with the second user; determining a comparison result when motion data of the second password data matches the motion data of the first password data; and allowing the second user to access, via the second computing device, an account associated with the first user, based on the comparison result.
3 . The method of claim 1 , further comprising: determining one or more variations between the motion data and the baseline motion data, the motion data considered as matching the baseline motion data; determining one or more non-motion data in the current visual input data associated with the motion data as the non-motion data for comparing to the baseline motion data; or determining the at least one authentication criterion based at least in part on profile information of the first user.
4 . The method of claim 1 , further comprising: instructing, by the one or more processors, an application executing on the first computing device associated with the first user to prompt the first user to perform a first motion that provides a video signature motion, via a camera of the first computing device, to generate the first password data; or instructing, by the one or more processors, an application executing on a second computing device associated with the second user to prompt the second user to perform a second motion, via a camera of the second computing device, to generate the second video password data.
5 . The method of claim 4 , wherein one or both of the first motion and the second motion comprise a three-dimensional (3D) pattern.
6 . The method of claim 4 , wherein the first user is prompted to perform the first motion with a physical object or with the physical object against a particular background.
7 . The method of claim 1 , further comprising: utilizing, by the one or more processors, a video password authentication machine learning model to determine that a second non-motion data of the second password data does not differ from the first non-motion data of the first password data; and instructing, by the one or more processors, an application executing on a second computing device associated with a second user to prompt the second user to perform an action to modify the second password data.
8 . The method of claim 7 , wherein the action comprises the second user performing a motion with a physical object that differs from a physical object associated with the first password data, or performing a motion against a background that differs from a background associated with the first password data.
9 . The method of claim 2 , wherein one or both of the first password data and the second password data are transmitted to the one or more processors via a SMS service.
10 . The method of claim 2 , wherein one or both of the first password data and the second password data are sharable with another user.
11 . The method of claim 2 , wherein one of the first password data and the second password data is captured by the first computing device associated with the first user and the second computing device associated with the second user, respectively.
12 . The method of claim 11 , wherein the first password data and the second password data are processed to: extract a set of motion data points to generate respective motion data; and represent respective non-motion data in a format that reduces a size of a data structure storing respective representation of the respective non-motion data.
13 . The method of claim 12 , wherein the format comprises a grey style video, a grey style image frame, a black and white video, or a black and white image frame.
14 . A system comprising: one or more processors; and a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to: obtain motion data of current visual input data that matches baseline motion data, and non-motion data of the current visual input data that differs from the baseline motion data based on at least one authentication criterion; receive a request to register a password of a first user from a first computing device, the request comprising first password data associated with the first user; establish a user-specific authentication criterion for the first user based on the first password data; receive a login attempt from a second computing device associated with a second user, the login attempt comprising second password data associated with the second user; determine a comparison result when a second motion data of the second password data differs from the non-motion data of the first password data based on the user-specific authentication criterion associated with the first user; and deny the login attempt of the second user to access, via the second computing device, an account associated with the first user based on the comparison result.
15 . The system of claim 14 , wherein the instructions further cause the one or more processors to: determine one or more variations between the motion data and the baseline motion data, the motion data considered as matching the baseline motion data; determine one or more non-motion data in the current visual input data associated with the motion data as the non-motion data for comparing to the baseline motion data; or determining the at least one authentication criterion based at least in part on profile information of the first user.
16 . The system of claim 14 , wherein the instructions further cause the one or more processors to: instruct an application executing on the first computing device to prompt the first user to perform a first motion that provides a video signature motion, via a camera of the first computing device, to generate the first password data; or instruct an application executing on the second computing device associated with the second user to prompt the second user to perform a second motion, via a camera of the second computing device, to generate the second password data.
17 . The system of claim 16 , wherein one or both of the first motion and second motion comprise a three-dimensional (3D) pattern.
18 . The system of claim 16 , wherein the first user is prompted to perform the first motion with a physical object or with the physical object against a particular background.
19 . The system of claim 14 , wherein the instructions further cause the one or more processors to: utilize a video password authentication machine learning model to determine that the non-motion data of the second password data does not differ from the non-motion data of the first password data; and instruct an application executing on the second computing device associated with the second user to prompt the second user to perform an action to modify the second password data.
20 . A non-transitory computer readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining steps of: obtaining, by one or more processors, motion data of current visual input data that matches baseline motion data and non-motion data of the current visual input data that differs from the baseline motion data based on at least one authentication criterion; receiving, by the one or more processors, a request to register a password of a first user from a first computing device, the request comprising first password data associated with the first user; establishing, by the one or more processors, a user-specific authentication criterion for the first user based on the first password data; receiving, by the one or more processors, a login attempt from a second computing device associated with a second user; determining a comparison result when the motion data of a second password data matches the motion data of the first password data based on the user-specific authentication criterion associated with the first user; and allowing the login attempt of the second user to access, via the second computing device, an account associated with the first user based on the comparison result.

Description

COPYRIGHT NOTICE A portion of the disclosure of this patent document contains material that is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever. The following notice applies to the software and data as described below and in drawings that form a part of this document: Copyright, Capital One Services, LLC., All Rights Reserved. FIELD OF TECHNOLOGY The present disclosure generally relates to improved computer-implemented methods, improved computer-based platforms or systems, improved computing components and devices configured for one or more practical technological improvement applications utilizing one or more machine learning techniques to authenticate user identities, including, but not limited to, via video passwords. BACKGROUND OF TECHNOLOGY A computer network platform/system may include a group of computers (e.g., clients, servers, computing clusters, cloud resources, etc.) and other computing hardware devices that are linked and communicate via software architecture, communication applications, and/or software applications associated with electronic transactions, data processing, and/or service management. For example, without limitation, a popular technique allowing users access to protected digital resources (e.g., an emails, a locked screen display) requires user identity authentication based on registered user credential information such as a username paired with a password. However, at least one technological problem is that the pair of username and password online/electronic/digital authentication technique is typically a subject of a tradeoff between providing secure identity authentication (e.g., less susceptible to various security attacks that may steal login credentials) while not over-burdening the user by the process of authentication (e.g., remembering a password too complicated, relying on a technologically advanced computing device to store an additional hardware/software token, or detect various biometrical information via sensors). SUMMARY OF DESCRIBED SUBJECT MATTER In some embodiments, the present disclosure provides various exemplary technically improved computer-implemented methods involving user authentication, the method including steps such as: obtaining, by one or more processors, a trained video password authentication machine learning model that determines: 1) when current motion data of current visual input data matches baseline motion data, and 2) when current non-motion data of the current visual input data associated with the current motion data differs from non-motion data associated with the baseline motion data based on at least one authentication criterion; receiving, by the one or more processors, a request to register a video password of a first user from a first computing device associated with the first user, the request comprising first video password data associated with the first user, the first video password data comprising: 1) first motion data, and 2) first non-motion data; establishing, by the one or more processors, at least one user-specific authentication criterion for the first user based on the first video password data; receiving, by the one or more processors, a login attempt from a second computing device associated with a second user who submits to be the first user, the login attempt comprising second video password data associated with the second user, the second video password data comprising: 1) second motion data, and 2) second non-motion data; utilizing, by the one or more processors, the trained video password authentication machine learning model to: determine a first comparison result when the second motion data of the second video password data matches the first motion data of the first video password data, and determine a second comparison result when the second non-motion data of the second video password data differs from the first non-motion data of the first video password data based on the at least one user-specific authentication criterion associated with the first user; and performing, by the one or more processors, one of: accepting the second user as the first user and allowing the login attempt of the second user to access, via the second computing device, an account associated with the first user, based on: i) the first comparison result or ii) the first comparison result and the second comparison result, rejecting the second user as the first user and denying the login attempt of the second user to access, via the second computing device, the account associated with the first user, based on: i) the first comparison result or ii) the first comparison result and the second comparison result. In some embodiments, the present disclosure also provides exemplary technically improved computer-ba