Capital One Services, LLC

Capital One Financial Corporation

Lawrence H Douglas

Paul Y Moreton

Thomas Christopher Clarke

Deborah Nally

Jeffrey Rule

Thomas S Poole

Jackson Macomber

Clayton Johnson

Luke A Hammock

Daniel Beck

Jeffrey M Samitt

Robert Dean Rowley, Iii

Philip Kim

Saejin Choi

Kaitlin J Newman

Hannes Mikael Jouhikainen

James M Ashfield

Ya Liu

Moshe Benjamin

John Fields

Eric Volles

Yolanda Liu

Justin Anthony Bowers

Joseph Whitchurch

Matthew R Brolund

John Elasic

Christopher Thomas Clarke

Anthony Swidler

Paul Young Moreton

Thomas Seeger Poole

Kevin Keenan

Iii Swidler Anthony

Drew Cogswell

Justin Bowers

Systems and methods to detect network activity deviations are described. The network activity data can include a set of network activities of a user and can be used to categorize the user into a segment. Deviations in the network activity can be detected based on one or more patterns of previous network activities of the user. For example, a value associated with the network activity can be determined to deviate from an expected value by a threshold value, determined based on the segment. Remediation to prevent the network activity from impacting future activities of the user can be determined based on scores of the network activity's participants, which includes the user. In an example, the network activity can be removed from an account of the user based on the determined remediation.

Network activity deviation detection and remediation

Systems and methods are described for performing secure communications with rotating key communications. For example, the system may receive a first applet request to perform a first rotating key communication across one or more computer networks to access a first server host. The system may then determine a first processing characteristic for the first applet request and a first plurality of server locations of the first server host (e.g., across the one or more computer networks). The system may then determine a first plurality of connection paths to a first subset of the first plurality of server locations. The system may then filter the first plurality of connection paths to generate a first subset of the plurality of connection paths. Based on the first subset of the plurality of connection paths, the system may generate a first rotating key for performing the rotating key communication.

Systems and methods for performing secure communications with rotating key communications

In some embodiments, a system may obtain first feedback indicating one or more first signal-strength-related results corresponding with one or more first token interactions occurring in connection with presentation of one or more first components at one or more first locations of a user interface of a user device. Based on the first feedback, the system may obtain one or more second locations of the user interface and cause presentation of one or more second components at the one or more second locations of the user interface. The system may obtain second feedback indicating one or more second signal-strength-related results corresponding with one or more second token interactions. Using the first and second feedback, the system may update a user interface presentation location at which to present a component for a token interaction within a profile associated with a user of the user device.

Systems and methods for facilitating wireless token interactions across multiple device types and/or token types

Systems and methods are described herein for leveraging offline virtual authentication tokens during periods of inaccessible network connectivity. In some aspects, after determining the system is offline, systems and methods request an authentication code from a user and determine whether the authentication code received from the user is valid. In response to determining that the authentication code is valid, systems and methods select an offline virtual authentication token from the plurality of stored offline virtual authentication tokens associated with the user account.

Systems and methods for leveraging offline virtual authentication tokens

Systems and methods for digital media-based user authentication are disclosed herein. In some aspects, the system may receive an authentication request. The system may transmit a user verification request based on the authentication request. The system may receive media recordings in response to the user verification request. The system may detect one or more features in the media recordings. The system may generate a plurality of risk metrics for the user based on generating risk metrics for the one or more features. The system may determine an authentication probability based on the plurality of risk metrics.

Systems and methods for digital media-based user authentication

Methods and systems are described herein for providing multi-tier machine learning model processing for document authenticity. A document authentication system built based on the current disclosure may rely on a camera to capture an image of a document and use a multi-tiered machine learning infrastructure to identify security features associated with the image of the document and determine based on those features whether the document is authentic. Furthermore, using the disclosed methods and system enable the provider of the machine learning model to improve the document authentication system by training the multi-tier machine learning model based on millions of interactions collected as part of processing. In addition, the document authentication system enables tracking where/when particular instances of documents are scanned. Based on the tracking, the document authentication system may further identify instances of documents that are not authentic.

Document authentication using multi-tier machine learning models

Methods and systems for preventing unauthorized resource access. In some aspects, the system obtains, in real time, a first data stream between a user requesting access to resources in a user account and an agent. The system processes, using a first machine learning model, the first data stream to generate a confidence score. If the confidence score exceeds a threshold, the system generates a sandbox context configured to simulate output indicative of successful resource access. The system obtains a second data stream for the sandbox context and processes it using a second machine learning model to determine whether the communication between the agent and the user was malicious. If the communication was not malicious, the system removes the user account from the sandbox context and effects grant of resource access. Otherwise, the system reports the agent and the user account for further processing for attempts to obtain unauthorized user access.

Systems and methods for preventing unauthorized resource access

A method and related system may analyze metadata associated with a first set of transactions to determine whether to perform a second set of transactions. The method and related system may include determining a data category based on first device-provided data of a first database transaction indicating a first record associated with a second record, and may further include obtaining, based on whether the data category satisfies a first set of criteria, an identifier and an amount based on image data using a prediction model. The method may further include querying a database based on the identifier to obtain an indication that the identifier is mapped to an object category, validating the amount based on a result indicating whether the object category satisfies a second set of criteria, and causing a second transaction that changes fields of the first and second records.

Augmented data for security during record updates

Systems and methods are provided for managing electronic tokens associated with an account. A system may include a memory storing instructions and account information associated with an account, and a processor configured to executed the stored instructions to: access information associated with one or more electronic tokens associated with the account, wherein the information includes one or more token settings, receive, via a network, information for a transaction request including a first token; analyze the received information to determine whether at least one rule in the one or more token settings is violated, responsive to a determination that at least one rule is violated, transmit an indication that the transaction request is denied, and responsive to a determination that no rules are violated, detokenize the transaction request.

Systems and methods for managing electronic transactions using electronic tokens and tokenized vehicles

Embodiments of the present disclosure provide systems, methods, and devices for countering fraudulent transactions by identifying devices associated with fraudulent activity. Examples relate to a system which compares identification parameters of devices associated with fraudulent activity, directly or indirectly, to identification parameters of a particular device. Based on the comparison, a confidence score may be generated may relate to the risk of fraud associated with that device. In some examples, the system may challenge a user with additionally security questions if the confidence score associated with a device indicates an increased risk of fraud.

Using common identifiers related to location to link fraud across mobile devices

A batteryless device is disclosed. According to certain embodiments, the batteryless device may include a first communication system and a second communication system, the second communication system being a near-field-communication (NFC) system. The batteryless device may also include a power receiver coupled to the first communication system and configured to wirelessly receive power from an external device for powering the first communication system. The batteryless device may further include a controller configured to: when the first communication system is powered, establish, via the first communication system, a first wireless connection with a user device; receive, through the first wireless communication, a token from the user device; establish, via the second communication system, a second wireless connection with a terminal; and transmit, through the second wireless connection, the token to the terminal.

Batteryless device with wirelessly powered token provisioning

A computing system may receive a request of the user for a first action of the user with an entity. In connection with granting the request of the user, the computing system may configure a token for use by the user and the entity such that (i) the entity is added as an approved entity, and (ii) the token is configured with a resource amount of the first action as a usage threshold of the token. The computing system may receive a request of the entity to use the token. The computing system may determine whether granting the request of the entity would cumulatively exceed the usage threshold of the token. Based on a determination that granting the request of the entity would not cumulatively exceed the resource usage of the token, the computing system may grant the request of the entity to use the token.

System and method for enabling multiple auxiliary use of an access token of a user by another entity to facilitate an action of the user

Systems and methods for successively executing an operation over multiple communication networks. In some aspects, the system obtains first access information received from a physical token and generates an operation related to an aggregated virtual container. The system determines a first communication network from the first access information and transmits, via the first communication network, the operation associated with the aggregated virtual container. If the operation was not transmitted successfully via the first communication network, the system obtains second access information received from the physical token, determines a second communication network from the second access information, and transmits, via the second communication network, the operation associated with the aggregated virtual container. If the operation was transmitted successfully via the second communication network, the system generates for display a notification that the operation has been executed.

Systems and methods for successively executing an operation over multiple communication networks

A system and method include a kiosk processor, a device kiosk on a customer mobile device, which displays via a user interface, content and options for the customer from a third party customer service system, a customer interaction channel that receives, via an associated customer interaction network, a request to access the third party customer service system, an authentication module associated with the kiosk processor that receives customer data and customer input associated with an authentication request to authenticate the customer, identifies a customer mobile device based on device identifiers, and evaluates risk factors associated with the customer mobile device, and a communication interface associated with the kiosk processor, that transmits, via a push notification gateway, a push notification to the device kiosk on the customer mobile device that establishes, via the network, a secure connection between the customer mobile device and the third party customer service system.

System and method for a kiosk in the mobile OS

Systems and methods for executing sequential suboperations over multiple communication networks. In some aspects, the system receives, via a first communication network, from an external system, an operation related to an aggregated virtual container. The system generates sequential suboperations including a first suboperation associated with a provider of the aggregated virtual container and the external system and a second suboperation associated with the user and the provider of the aggregated virtual container. If the first suboperation is executed successfully, the system transmits the second suboperation to a user system associated with the aggregated virtual container. If the second suboperation is executed successfully, the system generates a first message indicating that the operation has been executed and transmits the first message via the first communication network to the external system.

Growing community of inventors

McLean, VA, United States of America

Lawrence H Douglas