Capital One Services, LLC

Samuel Rapowitz

Viraj Chaudhary

Tyler Maiman

Joshua S Edwards

David Septimus

Jenny Melendez

Daniel Miller

Kevin Grant Osborn

Vyjayanthi Vadrevu

Xiaoguang Zhu

Daniel E Miller

Bryant Alan Yee

Armando Martinez Stone

Zviad Aznaurashvili

Joshua Peters

Alexander Lin

Purva Shanker

Julian Duque

John Jones

Dennis Liu

Steven Black

Zachary Sweeney

Jeffrey Rule

Shabnam Kousha

Kathryn Tikoian

Mia Rodriguez

Haytham Yaghi

Evelyn Burke

Caroline Williams

Maxwell Gotsch

Michael Gaba

Andrew Shelton

Ashleigh Choi

In certain embodiments, token data may be generated, updated, and presented on a token display of a token. In some embodiments, a communication session may be initiated between a token and a terminal. Authentication data stored on the token may be replaced with updated authentication data. Updated token data may be generated based on updated authentication data. The token data on an electrophoretic display may be replaced with the updated token data.

Token for generating and displaying updated authenticated token data on an electrophoretic display

Techniques for improved management of data may include the aggregation of connections with data sources, the aggregation of data, and/or the dynamic caching of data using data caching models. The caching model(s) may be adaptable based on data characteristics, user information, and/or usage information.

Account aggregation and caching systems and methods

The invention relates to generating cryptographic tokens based on characteristic determination. The system may generate and transmit a request for encrypted records from a blockchain node, receive the encrypted records from the blockchain node, decrypt the encrypted records into payload identifiers, retrieve sets of item identifiers based on the payload identifiers, determine characteristics associated with the sets of items, and generate a new cryptographic token that indicates the characteristics.

Systems and methods for user characteristic determination through cryptographic tokenized data

Systems and methods for recovery access to lost blockchain wallet seed phrases are disclosed. The systems and methods can store seed phrases for users for future retrieval. In some examples, a decentralized oracle creates an oracle private key that can be used to authenticate a user who is requesting the seed phrase. In some examples, the oracle creates a private/public key pair that can be used to transmit and store an encrypted version of the seed phrase. The authentication steps described herein also include knowledge-based authentication questions about the wallet, e.g., prior transactions using the wallet, value of the wallet, and the like.

Knowledge-based authentication for asset wallets

Methods, systems, and apparatuses are described herein for improving the security of personal information by preventing attempts at gleaning personal information from authentication questions. A computing device may receive a request for access to an account associated with a user. The request may comprise candidate authentication information. Based on comparing the candidate authentication information with the account data, the computing device may generate a synthetic authentication question. The synthetic authentication question may be generated as if the candidate authentication information is valid. A response to the synthetic authentication question may be received, and the request for access to the account may be denied.

Preventing unauthorized access to personal data during authentication processes

Aspects described herein may obfuscate publicly available personal information by publishing generated synthetic user personal data to one or more sites. By publishing the generated synthetic personal data to one or more sites, a user's actual personal data will be more difficult to discern and/or detect, resulting in greater privacy, security, and/or control of personal information. A machine learning model may be trained to generate synthetic personal data based on verified personal data and/or training datasets. Upon receiving a request from a user, the machine learning model may generate synthetic personal data, which appears similar to the publicly available information but includes false and/or inaccurate data and/or information about the user. The generated synthetic personal data and/or information may be disseminated to a plurality of sites to hide, or otherwise obfuscate, the user's actual data and/or information.

Scrambling an identity on the internet

In some implementations, an augmented reality device may establish a link with a transaction device. The augmented reality device may scan a surrounding environment to identify one or more objects in the surrounding environment using computer vision. The augmented reality device may determine, based on a notification that the transaction device was used to perform a transaction, a category associated with one or more objects that were identified in the surrounding environment at a time that the transaction was performed. The augmented reality device may send, to a transaction backend system, information that identifies a merchant category code (MCC) associated with the transaction based on the category associated with the one or more objects that were identified in the surrounding environment at the time that the transaction was performed.

Augmented reality techniques to identify a merchant category code associated with a transaction

Methods and systems are described herein for an access control system that may receive, from a device associated with a cryptography-based storage application, a blockchain operation request. The blockchain operation request may include an identifier of a cryptographic token (e.g., non-fungible token) that may store encrypted verification data encrypted using a public key associated with the cryptography-based storage application. The access control system may use an address associated with the cryptography-based storage application to send the verification data so that the verification data is decrypted and a first encoding of the decrypted data is generated by the device associated with the cryptography-based storage application. The access control system may then compare that first encoding with a second encoding made from the original verification data, and, based on the first encoding matching the second encoding, generate an authentication confirmation.

Sharing and requesting private data using cryptography

Systems and methods are directed to optimizing a security and recoverability trade-off generally associated with cryptocurrency master key storage. Exemplary embodiments provide a biometrically derived cryptographic seed using a measurement of one or more scale invariant biometric attributes associated with a user. The measured user biometric data is then processed into a repeatable biometric identifier and formatted into a (biometric) cryptographic seed, for derivation of a master extended private key, which may be stored in an HD wallet or used dynamically to conduct a blockchain transaction. The biometric seed and master key generation process may be facilitated by a mobile application responsive to a readout of biometric data from sensors integrated/associated with the mobile device. The captured biometric data may be cryptographically combined with a user-inputted password and/or an authentication data record wirelessly retrieved from an OTP card, to generate a cryptographic seed with greater security attributes.

Systems and methods for creating seed and master keys for blockchain wallets from user biometrics

The invention relates to generating cryptographic tokens based on received records. The system may receive a blockchain operation request comprising a plurality of records, encrypt a plurality of records into an encrypted payload, generate a cryptographic token based on the encrypted payload, and cause the cryptographic token to be committed to a blockchain.

Systems and methods for user control and exclusion of cryptographic tokenized data

Methods, systems, and apparatuses are described herein for improving computer authentication processes through the exclusion of certain merchants that may cause confusion. Indications of a plurality of different merchants, including merchant logos may be received. The indications may be processed to identify at least one similarity between a first merchant and a second merchant. A request for access to an account associated with a user and transaction data corresponding to the account may be received. Based on the similarity between the first merchant and the second merchant, at least one transaction corresponding to the first merchant may be removed to generate processed transaction record. An authentication question may be generated and a candidate response to the authentication question may be received. Based on the candidate response, access to the account may be provided.

Account authentication excluding merchants based on merchant logos

Disclosed embodiments may include a method for generating authentication quizzes. The method can comprise receiving an authentication request associated with a user. The method can further comprise requesting a transaction history associated with the user. The transaction history can comprise a first purchase of a first product and a second purchase of a second product. The method can include selecting the first product and the second product to authenticate the user and determining a third product that the user did not purchase. The method can generate images of the first product, the second product, and the third product based on SKU data and can generate an authentication quiz comprising the images of each product and requests to confirm if the user purchased the products recently or not. Upon receiving correct responses from the user, the method can comprise transmitting instructions to the user device to authenticate the user.

Systems and methods for generating authentication quizzes

Methods, systems, and apparatuses are described herein for improving the accuracy of synthetic authentication questions by analyzing third party account data. A request for access to a first account associated with a user may be received. The first account may be managed by a first organization. A transactions database might be queried for first account data. Second account data corresponding to a second account associated with the user might be received. That second account may be managed by a second organization different from the first organization. One or more second transactions, unique to the second account, may be identified. A synthetic transaction, configured to be different from transactions in the first account and the one or more second transactions, may be generated. An authentication question may be generated based on the synthetic transaction. Access to the first account might be provided based on a response to the authentication question.

Third party data processing for improvement of authentication questions

In some implementations, a device may obtain registration information, associated with an account, including one or more training handwriting samples of a user. The device may detect an initiation of an event associated with the account. The device may provide, to a terminal device associated with the event, the one or more authentication prompts to cause the terminal device to provide the one or more authentication prompts while the event is pending. The device may obtain, from the terminal device, one or more handwriting samples in response to the one or more authentication prompts. The device may determine, using a machine learning model, whether the user is associated with the event based on whether the one or more handwriting samples are in a handwriting of the user. The device may authenticate the event based on determining whether the one or more handwriting samples are in the handwriting of the user.

Account authentication using handwriting samples

Methods, systems, and apparatuses are described herein for improving computer authentication processes through presenting favorite merchants selection in transaction-based authentication. A computing device may receive a request for access to an account associated with a user. The computing device may train a machine learning model to determine predicted favorite merchant information, and provide one or more transactions conducted by the user as input to the trained first machine learning model. Data indicating favorite merchant information may be received from the trained first machine learning model. An authentication question may be generated and a candidate response to the authentication question may be received. Based on the candidate response, access to the account may be provided.

Growing community of inventors

Roswell, GA, United States of America

Samuel Rapowitz