Systems, methods, and computer program products are provided for secure inference in a multi-party computation (MPC) setting. The system may include at least one processor configured to receive data associated with a machine learning model, generate an approximation of a complex activation function of the machine learning model, generate an updated machine learning model based on the approximation of the complex activation function, and provide the updated machine learning model to a plurality of MPC nodes, wherein the plurality of MPC nodes perform an inference task using the updated machine learning model as part of an MPC protocol.
A method includes receiving from an access device in a transaction, a transaction value and a second address associated with the access device in a first interaction between the user device and the access device. The method also includes outputting the transaction value, and then generating a digital signature by signing a first address associated with the user device, the second address associated with the access device, and the transaction value with a user device private key associated with the first address. The user device then transmits, to the access device, a response message comprising the digital signature and the first address associated with the user device in a second interaction. The access device thereafter processes the transaction using the digital signature, the first address associated with the user device, the second address associated with the access device, and the transaction value.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
H04L 9/00 - Arrangements for secret or secure communicationsNetwork security protocols
3.
MULE-BASED FRAUD IDENTIFICATION SYSTEM AND METHOD THEREFOR
In some embodiemnts, a computer-implemented method, includes receiving, at a payment processor, an indication that a fraudulent transaction has occurred, the fraudulent transaction being associated with a fraudulent transaction account; performing, at the payment processor, a mule account assessment of financial transactions originating from an account that received the fraudulent transaction; utilizing the mule account assessment to identify whether the account that received the fraudulent transaction is a mule account; generating, at the payment processor, a mule account indicator indicative of the account that received the fraudulent transaction being identified as the mule account; and utilizing the mule account assessment to identify mule-adjacent accounts associated with the mule account, the identification of the mule-adjacent accounts being utilized to prevent mule-based fraud associated with the mule account.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
4.
Method, System, and Computer Program Product for Encapsulated Multi-Functional Framework
Methods, systems, and computer program products for encapsulated multi-functional framework: obtain a plurality of features associated with an instance, the plurality of features including a first subset of the plurality of features associated with a first entity, a second subset of the plurality of features associated with a second entity, and a third subset of the plurality of features associated with each of the first entity and the second entity; train, based on the plurality of features, a plurality of machine learning models encapsulated in a single framework; generate, based on a plurality of first weighted outputs, a plurality of second weighted outputs, and a plurality of third weighted outputs, a prediction for the instance; and provide the prediction for the instance.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
Provided is a system that includes a processor to receive a dataset comprising a plurality of feature values of a plurality of features; determine, for each feature of the plurality of features, a plurality of sequence deviation metrics; generate a plurality of sets of features for the plurality of sequence deviation metrics, wherein each set of features comprises a ranked set of features for a sequence deviation metric; train a plurality of machine learning models based on the plurality of sets of features, wherein the plurality of machine learning models comprises a machine learning model for each sequence deviation metric; determine a performance metric of each trained machine learning model for each sequence deviation metric; and select a ranked set of features for a sequence deviation metric that corresponds to a trained machine learning model that has a highest performance metric. Methods and computer program products are also provided.
Disclosed herein is a method for time-series data forecasting. The method may include processing a time-series dataset through a convolutional aggregation module, transforming an output of the convolutional aggregation module into a frequency-domain representation, segmenting the frequency-domain representation into a plurality of subsequences, modeling intra-period dynamics of each of the plurality of subsequences, modeling inter-period dynamics, generating a time-series forecast. In this embodiment, modeling intra-period dynamics may include the use of a shape bank module. Also disclosed herein is a system for forecasting spatio-temporal data.
A method includes loading a machine learning model having a set of parameters and trained using initial training data. A new set of training data may be used to determine a set of importance values for the set of petameters indicating a measure of importance for a given parameter to affect an accuracy of an output of the machine learning model. A first plurality of task-specific importance values can be loaded for a particular task using a respective task-specific training set. A second plurality of domain-specific importance values can be loaded for a particular domain using a respective domain-specific training set. Combined importance values can be determined for the set of parameters. The machine learning model can then be further trained using the combined importance values to determine fine-tuned values for the set of parameters.
A method includes obtaining time-dependent transaction data. After obtaining time-dependent transaction data, the method includes preprocessing the time-dependent transaction data to form pre-processed time-dependent transaction data. A training dataset is created from the pre-processed time-dependent transaction data. A sequence to sequence machine learning model is trained using the training dataset. Test time-dependent transaction data is input into the trained sequence to sequence machine learning model to obtain predicted time-dependent transaction data.
Automated systems and methods for monitoring computer networks via an intelligent widget, the system comprising an enterprise network comprising connected devices; the system configured to undertake a set of security monitoring activities for each of the connected devices, comprising instructions to detect a device of the connected devices logging into the enterprise network; detect a web call by the device to a web address via a proxy; generate a login log; generate a proxy log; combine data from the login log and the proxy log into concatenated data; aggregate the concatenated data from the device with concatenated data from the connected devices into aggregate data. The system comprising an admin device configured to receive the aggregate data to allow processing and display of selected content from the aggregate data; and display dynamically on a graphical user interface of the intelligent widget the selected content to monitor the enterprise network.
A method is disclosed. The method includes receiving from a resource provider computer, an authorization request message comprising a universal identifier and an amount, determining a credential linked to the universal identifier, generating an authentication request message comprising the universal identifier, and transmitting, to a first authorizing entity computer, the authentication request message. The method also includes receiving, from the first authorizing entity computer, an authentication response message comprising an indicator of positive authentication, and then transmitting a subsequent authorization request message comprising the credential and the amount to a second authorizing entity computer. The method also includes receiving, from the second authorizing entity computer, an authorization response message comprising the credential, modifying the authorization response message to include the universal identifier instead of the credential, and transmitting, to the resource provider computer, the modified authorization response message.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
Described are a system, method, and computer program product for real-time change detection. The system includes at least one processor configured to receive transaction data associated with a transaction associated with an entity, and determine an aggregate value based on a portion of the transaction data for the transaction. The at least one processor is also configured to generate a predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model. The at least one processor is further configured to determine a deviation of the aggregate value from the predicted aggregate value, and compare the deviation to a dynamic threshold associated with the entity. The at least one processor is further configured to, in response to determining that the deviation satisfies the dynamic threshold, trigger a risk mitigation process associated with the entity.
Described are a system, method, and computer program product for efficient node embeddings for use in predictive models. The method includes receiving graph data associated with a graph comprising a plurality of nodes associated with a plurality of entities and a plurality of edges associated with interactions between entities. The method also includes generating a plurality of node embeddings for the plurality of nodes, and generating a matrix based on each positive pair of nodes and the plurality of node embeddings. The method further includes decomposing the matrix to provide a left unitary matrix, a diagonal matrix, and a right unitary matrix. The method further includes determining a plurality of updated node embeddings for the plurality of nodes based on the left unitary matrix and the diagonal matrix. The method further includes communicating the plurality of updated node embeddings for inputting into a machine learning model to generate a prediction.
Provided is a system, method, and computer program product for automatically updating credentials. The system includes at least one processor programmed or configured to receive, from a first issuer system, a migration request identifying an original account identifier, a new account identifier, and a credential request history associated with the original account identifier, analyze the credential request history to identify at least one provisioned credential associated with the original account identifier, the at least one provisioned credential including at least one of a card-on-file merchant credential and a device token, and in response to identifying the at least one provisioned credential, automatically generate an update request configured to cause at least one of the following to update the at least one provisioned credential based on the new account identifier: a merchant system, a payment gateway associated with a merchant system, a user device, or any combination thereof.
A method for facilitating online payments includes detecting, by a browsing environment, payment data input fields on a checkout page within the browsing environment; sending, by the browsing environment, a user identifier to a tokenization platform; retrieving, by the browsing environment, a tokenized payment data generated by the tokenization platform based on the user identifier; populating, by the browsing environment, the payment data input fields on the checkout page with values based on the retrieved tokenized payment data. The method also includes submitting, by the browsing environment, the values to a merchant backend system for processing. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each configured to perform the actions of the methods.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06Q 20/12 - Payment architectures specially adapted for electronic shopping systems
G06Q 20/14 - Payment architectures specially adapted for billing systems
Method, system, and computer program product for providing an analysis framework for cybersecurity threats using a hybrid temporal graph neural network
Methods, systems, and computer program products are provided for an analysis framework for cybersecurity threats in a network. A method may include receiving data associated with network activity of each user of a plurality of users during a time interval, generating one or more entity feature embeddings for each user based on the data associated with network activity of that user, generating a plurality of user behavior embeddings for the plurality of users based on one or more outputs of a temporal graph neural network (GNN) machine learning model, and calculating a user risk score for a first user based on the plurality of user behavior embeddings, wherein the user risk score represents a measurement of a risk associated with behavior of the first user to cause damage to a network.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
16.
METHOD FOR USER DEVICE AND ACCESS DEVICE INTERACTION
Described herein is a method performed by a user device that interacts with an access device. The user device determines input data at a plurality of sensors included in the user device in response to a movement of the user device by a user. Using a trained machine learning model, the user device classifies the input data as being a specific movement pattern of a plurality of specific movement patterns. The user device identifies an access data instance associated with the specific movement pattern. Further, the user device transmits, using a first RF antenna, the access data instance to an access device comprising a second RF antenna. The access device in turn generates an authorization request message comprising the access data instance.
Apparatus, system, and method for generating a synthetic finger are disclosed. A three-dimensional (3D) model of a fingerprint is generated based on fingerprint data received from a database. A mold is creating based on the 3D model. A casting material is applied on the mold to create a synthetic finger. The synthetic finger includes a fingerprint formed on the casting material by the mold.
The present disclosure relates to a payment processing system and a method for automatic payment method transmission to merchants. The method comprises providing a list of plurality of merchants to a user for receiving a user selection on at least one of the plurality of merchants for performing one or more transactions. In response to the user selection, the method comprises authenticating the user, based on user details provided by the user, for authorizing the user to set one or more payment methods for the at least one of the plurality of merchants selected by the user. Subsequently, method comprises transmitting the user details, user authorization and the one or more payment methods set by the user to a payment processor associated with each of the plurality of merchants selected by the user. Finally, the method comprises receiving a merchant confirmation on acceptance of the one or more payment methods set by the user from the at least one of the plurality of merchants selected by the user. In some embodiments, the above process may be also used to delete the one or more payment methods set with the plurality of merchants selected by the user and/or delete a merchant from the list of the plurality of merchants selected by the user.
A system and method for network authentication using device level authentication controls. The method comprises receiving a first payment transaction request from a user device. The method comprises, enabling the authentication mode for the user to perform an authentication using the selected authentication mode and generating a key pair for linking with the enabled authentication mode for further authentication of the user device in one or more further transaction requests. The method further comprises generating an enrolment completion message and executing the first payment transaction request upon successful signing using the linked key pair. In this manner, the present disclosure may be configured to utilize device authentication data as a part of network authentication risk checks leading to providing a more secure way of completing a transaction.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
20.
MITIGATING DEEP LEARNING MODEL BIAS VIA CONTRASTIVE LEARNING
Methods and systems for training machine learning models using contrastive loss are disclosed. The use of these novel contrastive loss methods can improve the accuracy of prediction models trained using such methods. During training, training data elements can be grouped into pairs of training data elements, and a computer system can determine whether such pairs comprise "positive" pairs of training data elements or "negative" pairs of training data elements. Embeddings can be generated for each pair of training data elements using an encoder, and a contrastive loss can be calculated between each pair of embeddings, such that the encoder is rewarded for generating similar embeddings for positive pairs of training data elements and penalized for generating similar embeddings for negative pairs of training data elements. Using contrastive loss, the machine learning model can be trained to develop a more holistic understanding of the training dataset, thereby improving accuracy.
Systems and methods for securely activating a physical card capable of NFC are disclosed. These may comprise authenticating, by a mobile device capable of NFC communication, a user via an issuer application on the mobile device; determining, by the mobile device, based on user data available to the issuer application, that the user has been issued the physical card, wherein the physical card is inactive and NFC-enabled; prompting, the user, by the mobile device, to place the physical card within a communication distance to the mobile device; detecting, by the mobile device, the physical card within the communication distance to the mobile device; executing, by the mobile device, an NFC-based ODA transaction with the physical card; based on a success of the ODA transaction, authenticating, by the mobile device, a validity of the physical card with the issuer, to allow activation of the card.
G06Q 20/34 - Payment architectures, schemes or protocols characterised by the use of specific devices using cards, e.g. integrated circuit [IC] cards or magnetic cards
H04W 4/80 - Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
22.
RAPID VALUE TRANSFER BETWEEN DIFFERENT VALUE SYSTEMS
In systems and methods for efficient remittance, a server computer receives, from a first issuer computer via an application programming interface (API), a request to transfer an amount of first currency to a receiving party. The server computer obtains an amount of digital currency corresponding to the amount of first currency and records a record of the transfer to a ledger of interactions. The server computer causes the record to be recorded to a blockchain. The server computer transmits, to a second issuer computer, a notification of the transfer and receives, from the second issuer computer via the API, a request for an amount of second currency corresponding to the amount of digital currency. The server computer transmits the amount of the second currency to the second issuer computer, causing the second issuer computer to provide the amount of second currency to the receiving party.
G06Q 20/10 - Payment architectures specially adapted for electronic funds transfer [EFT] systemsPayment architectures specially adapted for home banking systems
G06Q 20/06 - Private payment circuits, e.g. involving electronic currency used only among participants of a common payment scheme
Systems, methods, and computer program products are provided for detecting anomalies in computing systems using correlated session data from source servers and target servers. The method includes receiving a connection request for a connection to a target server from a source server, the connection request including a login request to a service account on the target server, the connection request initiated on the source server by a user account; generating a communication session for the user account between the source server and the target server based on the connection request; collecting target server session data associated with the target server and source server session data associated with the source server; correlating the target server session data with the source server session data to provide correlated session data; and detecting an anomaly based on the correlated session data.
A system and method are provided which include receiving, by a user device comprising a first data processor, a memory storing portable device information, and a first transceiver coupled to the first data processor, data associated with a portable device, the portable device comprising a second data processor and a second transceiver, the data obtained while the user is viewing the portable device; determining, by the first data processor, that the data comprises information corresponding to the portable device information stored in the memory; and responsive to the determining, transmitting, by the user device to the portable device via a short range communication protocol, an instruction to the portable device.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04W 12/33 - Security of mobile devicesSecurity of mobile applications using wearable devices, e.g. using a smartwatch or smart-glasses
Embodiments of the present disclosure are directed to methods and systems for biometric authentication using superimposed biometric data. Using such methods and systems, a user can be authenticated for some purpose (e.g., gaining access to a secure facility, accessing a user account, etc.). Superimposed biometric data, unlike conventional biometric data, can comprise a combination of user biometric data and artificial biometric data. This combination can protect the user biometric data. For example, if an identity thief manages to acquire the superimposed biometric data, it may be difficult or impossible for the identity thief to acquire the user biometric data, thereby protecting the user's data privacy. The user can use a user device to capture and combine the user's biometric data with artificial biometric data stored on the user device, thereby determining superimposed biometric data, which can be sent to a biometric authentication server in order to authenticate the user.
In some embodiments, a system includes a processor and a non-transitory computer readable medium coupled to the processor, the non-transitory computer readable medium comprising code that constructs a minimum perfect hash (MPH)-based database file for use in an MPH database; generates, based upon MPH-based parameters, an MPH-based record for the MPH database file; generates, based on an MPH function and a first parameter of the MPH-based parameters and a second parameter of the MPH-based parameters, an MPH-based position index that maps to the MPH-based record; and utilizes the MPH-based position index to access the MPH-based record in the MPH database.
Systems, methods, and computer program products are provided for determining attention patterns in state space models. An example system includes at least one processor to receive input data for a state space machine learning model, generate an input sequence for the state space machine learning model based on the input data, where the input sequence includes a sequence of tokens associated with the input data, assign a plurality of weights to the sequence of tokens of the input sequence, provide the input sequence to a first block of the state space machine learning model, obtain an attention matrix based on the first block of the state space machine learning model, and display an attention pattern based on the attention matrix in a user interface.
Provided is a system that includes a processor to provide a first input to an autoencoder machine learning model; generate a first output of the autoencoder machine learning model based on the first input; provide the first input to a production machine learning model; provide the first output of the autoencoder machine learning model as a second input to the production machine learning model; generate a first output of the production machine learning model based on the first input; generate a second output of the production machine learning model based on the second input; determine a metric of divergence between the first output and the second output of the production machine learning model, wherein the metric of divergence comprises an indication of whether the first input is associated with an adversarial attack; and perform an action. Methods and computer program products are also provided.
Provided are systems, methods, and computer program products for authenticating a transaction based on behavioral biometric data. An example system includes a processor of a transaction service provider system configured to receive an authorization request message. The processor is also configured to communicate a request to a computing device for a user response to a second factor authentication process. The processor is further configured to determine that an additional security authentication should be applied. The processor is further configured to communicate an authenticity assessment request to a behavioral biometrics server computer. The processor is further configured to receive, from the behavioral biometrics server computer, an authenticity assessment response. The processor is further configured to generate an authentication response message to an issuer system configured to authenticate the transaction when authenticity assessment data is evaluated by the issuer system in combination with the user response to the second factor authentication process.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
31.
System, Method, and Computer Program Product for Early Detection of a Merchant Data Breach Through Machine-Learning Analysis
Provided are systems, methods, and computer program products for early detection of a merchant data breach through machine-learning analysis. An example system includes a processor configured to receive transaction authorization request data. The processor is also configured to generate a metric based on security-testing transaction activity. The processor is further configured to generate features for training one or more models. The processor is further configured to generate a first dataset based on the features and associated with a plurality of merchants, and a second dataset based on the features and associated with a previously breached merchant. The processor is further configured to train an ensembled model to associate merchants with a likelihood of data breach. The processor is further configured to determine a breached merchant, automatically freeze a transaction, retrain the ensembled model, and determine another breached merchant based on the updated models.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06F 21/55 - Detecting local intrusion or implementing counter-measures
Methods and systems for performing efficient privacy-preserving machine learning (or other computationally intensive private computing operations) based on homomorphic encryption are disclosed. Two computer systems can collectively perform these methods on behalf of a client computer using threshold leveled homomorphic encryption (LHE) or fully homomorphic encryption (FHE), e.g., using the Cheon-Kim-Kim-Song cryptosystem. For example, two computer systems could privately evaluate a client's encrypted inputs using a machine learning model and return an encrypted output to the client, preserving the privacy of the client's data. Methods according to embodiments include efficient bootstrapping methods, ciphertext packing methods, encryption parameter optimization methods, and methods for privately fine-tuning machine learning models using low rank adaptation (LoRA). Embodiments improve the speed and efficiency of private HE-based computation, which are often several orders of magnitude slower than non-private computation.
A method is disclosed. The method includes receiving, by a user device from an energy supply terminal, transaction data comprising an energy provider identifier for a transaction to provide energy from the energy supply terminal to a vehicle. The user device then determines a credential, and then transmits the energy provider identifier and a selection of the credential to a secure remote transaction server. The secure remote transaction server initiates transmission of an authorization request message comprising the energy provider identifier, the credential or a token corresponding to the credential, and an amount to an authorizing entity computer. The secure remote transaction server then receives an authorization response message for the transaction from the authorizing entity computer. The secure remote transaction server can also provide an indication of the authorization for the transaction the user device.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
Methods and systems for provisioning a token on a mobile device without the installation of an application thereon are provided. A server computer can: receive credentials associated with a user account; encrypt the credentials; generate a payload in form of a remote resource address; generate an application associated with the remote resource address; transmit the application to a mobile device in response to the mobile device navigating to the remote resource address; receive the payload from the application when the application is executed on the mobile device; and provision a token associated with the user account on a digital wallet of the mobile device when the application is executed on the mobile device without being installed thereon.
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
The present disclosure provides various cards (e.g., payment cards, identification cards, driver's license cards) that are removably attachable to a portable electronic device. In some aspects, the portable electronic device is configured for reverse wireless charging and includes a device charging coil. The card includes a card charging coil, a capacitor electrically coupled to the card charging coil, and a circuit. The card charging coil can produce a current from magnetic flux generated by the device charging coil. The circuit can cause the capacitor to charge when the card is attached to the portable electronic device and cause the capacitor to discharge upon removal of the card from the portable electronic device.
G06K 19/07 - Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards with integrated circuit chips
G06Q 20/42 - Confirmation, e.g. check or permission by the legal debtor of payment
Embodiments provide techniques for automatically pushing a dynamic card art to a newly provisioned or existing credential on a digital wallet. The dynamic card art may be associated with a triggering event or timeline. Upon occurrence or completion of the triggering event, the dynamic card art may be automatically pushed to the digital wallet, and the representation of the credential on the digital wallet may be updated using the dynamic card art.
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
One embodiment is related to a method. The method includes receiving from a storage application server computer, a token request message comprising a user identifier associated with a storage application on a user device, and determining a token. The token is a limited use token. The method includes mapping the token to the user identifier, transmitting to the user device, a token response message comprising the token to the storage application server computer. The method includes receiving from a processing network computer, a de-tokenization request message comprising the token, after the processing network computer receives an authorization request message comprising the token from a resource provider computer via a transport computer. The method also includes determining the user identifier using the token, and transmitting the user identifier to the processing network computer.
Methods, systems, and computer program products are provided for augmenting embeddings which include: receiving a data set; identifying a contextual partition of the data set; partitioning the data set into partitions; inputting the contextual partition and the partitions into an embedding model; generating an embedding for each of the contextual partition and the partitions to form a contextual partition embedding and partition embeddings; augmenting each of the partition embeddings by appending the contextual partition embedding to each of the partition embeddings; storing the augmented partition embeddings in a database; receiving a query associated with the data set; in response to receiving the query, searching the augmented partition embeddings based on the query; and automatically identifying an augmented partition embedding relevant to the query based on the searching.
A method is disclosed. The method includes A method is disclosed. The method can include receiving, by a hub computer, a first user account identifier from a first service provider computer in communication with a first user device, and also in communication with a first blockchain network. The first service provider computer can transfer an amount of digital currency to a first smart contract on the first blockchain network. The hub computer can also receive a second user account identifier from a second service provider computer in communication with a second user device, and also a second blockchain network containing a second smart contract. The hub computer may receive a first amount of a first digital currency from the first service provider computer, and may then transfer a second amount of a second digital currency to the second service provider computer.
G06Q 20/10 - Payment architectures specially adapted for electronic funds transfer [EFT] systemsPayment architectures specially adapted for home banking systems
G06Q 20/06 - Private payment circuits, e.g. involving electronic currency used only among participants of a common payment scheme
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
40.
System, Method, and Computer Program Product for Generating an Inference Using a Machine Learning Model Framework
Provided is a system for generating an inference based on real-time selection of a machine learning model using a machine learning model framework that includes at least one processor programmed or configured to receive a request for inference, wherein the request includes a payload, select a machine learning model of a plurality of machine learning models based on the request for inference, determine an aggregation of data based on the machine learning model and the payload of the request, transform the aggregation of data into inference data, wherein the inference data has a configuration that is capable of being processed by the machine learning model, and generate an inference based on the inference data using the machine learning model. Methods and computer program products are also provided.
Methods, systems, and computer program products for universal depth graph neural networks may obtain a graph G including an adjacency matrix A and an attribute matrix X and train a graph convolutional network using according to the following updating Equation: H=σ(ŜdXW), where H is an output embedding matrix, σ(⋅) is a nonlinear activation function, Ŝ is a filter, X is an attribute matrix, W is a trainable weight matrix, and d is a trainable depth parameter.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
36 - Financial, insurance and real estate services
Goods & Services
(1) Promoting sporting events, musical concerts, and other entertainment events of others; arranging for preferred benefits and privileges to live entertainment and sporting events; promoting the goods and services of others through the administration of customer loyalty and incentive programs featuring access to pre-sale opportunities and exclusive events.
(2) Financial, monetary and banking services; insurance services; real estate services; electronic credit and debit card transaction processing, electronic funds transfer, smart card services and electronic cash transaction services, including payment card authorization services, funds verification services, payment processing services in the field of credit card and debit card payments, credit card and debit card transaction processing services, payment transaction settlement services; payment processing services including authorization services, verification services, transaction processing services, transaction settlement services; processing of financial transactions online via a global computer network and via telecommunication, mobile and wireless devices; payment transaction authentication and verification services; dissemination of financial information and electronic payment data via a global computer network and via telecommunication, mobile and wireless devices; financial services, including banking, credit card, debit card, and bill payment services.
36 - Financial, insurance and real estate services
45 - Legal and security services; personal services for individuals.
Goods & Services
(1) Providing a website featuring curated selections of goods and experiences for purchase; sourcing and procuring services; sourcing and procurement of curated goods and experiences for others; personal concierge services for others; sourcing and procuring curated goods and experiences.
(2) Financial, monetary and banking services; insurance services; real estate services; electronic credit and debit card transaction processing, electronic funds transfer, smart card services and electronic cash transaction services, including payment card authorization services, funds verification services, payment processing services in the field of credit card and debit card payments, credit card and debit card transaction processing services, payment transaction settlement services; payment processing services including authorization services, verification services, transaction processing services, transaction settlement services; processing of financial transactions online via a global computer network and via telecommunication, mobile and wireless devices; payment transaction authentication and verification services; dissemination of financial information and electronic payment data via a global computer network and via telecommunication, mobile and wireless devices; financial services, including banking, credit card, debit card, and bill payment services.
41 - Education, entertainment, sporting and cultural services
Goods & Services
Promoting of a customer loyalty program and preferred customer program for payment card holders; administration of consumer loyalty and incentive programs to promote access to selected lounges, clubs, hospitality venues, and other physical environments; providing marketing and promotional information regarding cardholder benefits and access opportunities. Entertainment services, namely, providing eligible cardholders with access to entertainment venues, cultural venues, and special events; arranging and conducting special events for business, social entertainment, and cultural purposes for cardholders; club services, namely, providing facilities for entertainment and social gatherings for cardholders.
Promoting sporting events, musical concerts, and other entertainment events of others; arranging for preferred benefits and privileges to live entertainment and sporting events; Promoting the goods and services of others through the administration of customer loyalty and incentive programs featuring access to pre-sale opportunities and exclusive events.
Promoting sporting events, musical concerts, and other entertainment events of others; arranging for preferred benefits and privileges to live entertainment and sporting events; Promoting the goods and services of others through the administration of customer loyalty and incentive programs featuring access to pre-sale opportunities and exclusive events.
36 - Financial, insurance and real estate services
41 - Education, entertainment, sporting and cultural services
Goods & Services
(1) Promoting of a customer loyalty program and preferred customer program for payment card holders; administration of consumer loyalty and incentive programs to promote access to selected lounges, clubs, hospitality venues, and other physical environments; providing marketing and promotional information regarding cardholder benefits and access opportunities.
(2) Financial, monetary and banking services; insurance services; real estate services; electronic credit and debit card transaction processing, electronic funds transfer, smart card services and electronic cash transaction services, including payment card authorization services, funds verification services, payment processing services in the field of credit card and debit card payments, credit card and debit card transaction processing services, payment transaction settlement services; payment processing services including authorization services, verification services, transaction processing services, transaction settlement services; processing of financial transactions online via a global computer network and via telecommunication, mobile and wireless devices; payment transaction authentication and verification services; dissemination of financial information and electronic payment data via a global computer network and via telecommunication, mobile and wireless devices; financial services, including banking, credit card, debit card, and bill payment services.
(3) Entertainment services; providing eligible cardholders with access to entertainment venues, cultural venues, and special events; arranging and conducting special events for business, social entertainment, and cultural purposes for cardholders; club services; providing facilities for entertainment and social gatherings for cardholders.
36 - Financial, insurance and real estate services
Goods & Services
(1) Promoting sporting events, musical concerts, and other entertainment events of others; arranging for preferred benefits and privileges to live entertainment and sporting events; promoting the goods and services of others through the administration of customer loyalty and incentive programs featuring access to pre-sale opportunities and exclusive events.
(2) Financial, monetary and banking services; insurance services; real estate services; electronic credit and debit card transaction processing, electronic funds transfer, smart card services and electronic cash transaction services, including payment card authorization services, funds verification services, payment processing services in the field of credit card and debit card payments, credit card and debit card transaction processing services, payment transaction settlement services; payment processing services including authorization services, verification services, transaction processing services, transaction settlement services; processing of financial transactions online via a global computer network and via telecommunication, mobile and wireless devices; payment transaction authentication and verification services; dissemination of financial information and electronic payment data via a global computer network and via telecommunication, mobile and wireless devices; financial services, including banking, credit card, debit card, and bill payment services.
36 - Financial, insurance and real estate services
37 - Construction and mining; installation and repair services
43 - Food and drink services, temporary accommodation
Goods & Services
(1) Financial, monetary and banking services; insurance services; real estate services; electronic credit and debit card transaction processing, electronic funds transfer, smart card services and electronic cash transaction services, including payment card authorization services, funds verification services, payment processing services in the field of credit card and debit card payments, credit card and debit card transaction processing services, payment transaction settlement services; payment processing services including authorization services, verification services, transaction processing services, transaction settlement services; processing of financial transactions online via a global computer network and via telecommunication, mobile and wireless devices; payment transaction authentication and verification services; dissemination of financial information and electronic payment data via a global computer network and via telecommunication, mobile and wireless devices; financial services, including banking, credit card, debit card, and bill payment services.
(2) Providing online reservations and bookings for curated dining experiences; Membership club services for payment cardholders featuring restaurant services, including dining events and restaurant openings; providing information related to restaurants and dining services.
43 - Food and drink services, temporary accommodation
Goods & Services
Providing online reservations and bookings for curated dining experiences; Membership club services for payment cardholders featuring restaurant services, namely, dining events and restaurant openings; providing information related to restaurants and dining services
Providing a website featuring curated selections of goods and experiences for purchase; Sourcing and procuring services, namely, sourcing and procurement of curated goods and experiences for others; Personal concierge services for others, namely, sourcing and procuring curated goods and experiences.
52.
SYSTEM AND METHOD EMPLOYING REDUCED TIME DEVICE PROCESSING
Methods and systems for facilitating a transaction are provided. A transaction involving an integrated circuit user device in contact with an access device is processed in less time, such that the user device can be removed at an earlier time. In embodiments, an access device provides an estimated value to a user device such that a cryptogram can be generated without waiting for a final value. Additionally, the access device can store user device data and then complete the transaction with the user device before authorizing the transaction, such that the user device can be removed without waiting for an authorization response.
G06Q 20/34 - Payment architectures, schemes or protocols characterised by the use of specific devices using cards, e.g. integrated circuit [IC] cards or magnetic cards
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
53.
EXTEND PROVISIONING AND DEVICE BINDING CONSENT FOR DEVICE TOKENS WITH PASSKEY
A computer receives a token provisioning request message from a token requestor computer. The token provisioning request message requests provisioning of a device token to a user device. The computer receives authentication information from the user device via the token requestor computer. The computer validates the authentication information. If the authentication information is valid, the computer activates the device token. The computer activates one or more additional tokens based on a pre-determined list of additional tokens associated with the token requestor computer. The computer generates a token activation message that indicates whether or not each token is active. The computer provides the token activation message to the token requestor computer.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
Embodiments of the invention are directed to a stored value device with increased data security by limiting access to access data. A stored value device may omit a magnetic stripe, and may not display access data. The stored value device can maintain functionality through chip-based communications, and the user can conduct online and/or mobile transactions by obtaining a token and/or virtual access data. The stored value device may be inactive until obtained be a user and activated through one or more activation processes. Modes in which the stored value device can be utilized can be limited to protect data.
G06F 21/35 - User authentication involving the use of external additional devices, e.g. dongles or smart cards communicating wirelessly
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
55.
PROBABILISTIC BITMAPS FOR EFFICIENT DATA COMPARISON
A computer-implemented method processes transaction data using probabilistic structures. The method involves generating a probabilistic bitmap from transaction attributes, which are then organized in a specific order. This bitmap is used to perform transaction data checks by comparing it with other probabilistic bitmaps from different systems. The process includes hashing attribute values, applying a Mod function, and organizing bits to represent these values. The method allows for detecting mismatches or inconsistencies without directly comparing transaction data, thus identifying issues like missing or corrupted data. Additionally, the method supports updating bitmaps with new data and generating reports based on these checks.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
A method is disclosed. The method includes obtaining, by a user device comprising a storage application, a verifiable credential comprising an attestation comprising access data. The attestation can be a network token attestation or storage application attestation. The method can further include transmitting, by the user device to a resource provider computer, the verifiable credential. The resource provider computer processes an interaction using the verifiable credential.
A method is disclosed, and includes receiving, at a resource access system, from a machine learning model requestor, a request for a machine learning model. The request for the machine learning model includes a query and a training data set. The method also includes determining based on the query and using natural language processing, a model cache query, and determining a machine learning model. The machine learning model is determined by searching a model cache using the model cache query. The method also includes transmitting, by the resource access system, the machine learning model to the machine learning model requestor.
A computer-implemented method processes transaction data using probabilistic structures. The method involves generating a probabilistic bitmap from transaction attributes, which are then organized in a specific order. This bitmap is used to perform transaction data checks by comparing it with other probabilistic bitmaps from different systems. The process includes hashing attribute values, applying a Mod function, and organizing bits to represent these values. The method allows for detecting mismatches or inconsistencies without directly comparing transaction data, thus identifying issues like missing or corrupted data. Additionally, the method supports updating bitmaps with new data and generating reports based on these checks.
G06F 18/2415 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
A method is disclosed. The method includes receiving, by a token processing system from a token requestor computer comprising a storage application, a token provisioning request comprising a credential associated with a record. The method also includes determining, by the token processing system, a first token and a second token. The method also includes transmitting, by the token processing system, a token provisioning response message comprising the first token and the second token to the token requestor computer for storage in the storage application. The first token and the second token have different formats.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
G06F 21/33 - User authentication using certificates
Embodiments can perform a database join that allows secret shared database join between a database table with a unique matching column and a database table with a non-unique matching column (i.e., contains unbounded repeats of values).
Systems, methods, and computer program products are provided for generating large scale embeddings for large foundational machine learning models. An example system may include at least one processor configured to, for each identifier of a plurality of identifiers, provide data associated with an identifier as an input to a first neural network model, provide the data associated with the identifier as an input to a second neural network model, determine a first embedding for the identifier based on the output of the first neural network model, the first embedding representing a primary category of transaction behavior associated with the identifier, determine a second embedding for the identifier based on the output of the second neural network model, the second embedding representing a characterization of the transaction behavior associated with the identifier, and generate an output of a final machine learning model based on data associated with a transaction record.
One embodiment of the present disclosure may include a method for providing access to resources by a resource provider computer during a first web session with a client device. The resource provider can provide a first web page to the client device, the first web page including a first option to complete a first access request with the resource provider computer as a guest for access to a first resource. The resource provider computer can receive a first selection of the first option from the client device and provide a second web page including a second option to remember the user device. The resource provider computer can, in response to receiving a second selection of the second option from the client device, send a remember flag to a server computer. The resource provider computer can then receive a recognition identifier from the server computer and store the recognition identifier.
H04L 67/146 - Markers for unambiguous identification of a particular session, e.g. session cookie or URL-encoding
G06Q 20/02 - Payment architectures, schemes or protocols involving a neutral third party, e.g. certification authority, notary or trusted third party [TTP]
G06Q 20/12 - Payment architectures specially adapted for electronic shopping systems
Systems and methods perform on-chain authorization. A server computer receives, from a computing device via a first Application Programming Interface (API), a request to authorize a transfer on a distributed ledger from a first digital wallet of a first user to a second digital wallet of a second user. The server computer validates the request and stores an authorization record to the distributed ledger. The server computer receives a request for authorization details from the computing device via a second API. The server computer retrieves the authorization record from the distributed ledger and transmits the authorization details based on the authorization record to the computing device. The computing device thereafter approves a pull request to pull an amount from the first digital wallet to the second digital wallet based on the authorization details.
G06Q 20/06 - Private payment circuits, e.g. involving electronic currency used only among participants of a common payment scheme
G06Q 20/10 - Payment architectures specially adapted for electronic funds transfer [EFT] systemsPayment architectures specially adapted for home banking systems
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06Q 20/02 - Payment architectures, schemes or protocols involving a neutral third party, e.g. certification authority, notary or trusted third party [TTP]
H04L 9/00 - Arrangements for secret or secure communicationsNetwork security protocols
64.
Method, System, and Computer Program Product for Identifying Sub-Merchants Within a Global Merchant Repository
Provided are methods for identifying sub-merchants within a Global Merchant Repository (GMR) that include receiving sub-merchant data associated with one or more sub-merchants, from one or more payment facilitators associated with a plurality of sub-merchants, where the sub-merchant data comprises a Card Acceptor Identifier (CAID) associated with each of the one or more payment facilitators, assigning a plurality of pseudo acquirer identifiers to the sub-merchant data received from each of the one or more payment facilitators, and identifying the one or more sub-merchants in the GMR by mapping the sub-merchant data with transaction data associated with a plurality of merchants in the GMR, based on the plurality of pseudo acquirer identifiers and the CAID associated with the respective payment facilitators. Systems and computer program products are also disclosed.
Embodiments of the invention are directed to systems, methods, and devices for providing dynamic applicability management with respect to a testing framework. Executable code segments can be provided in/with various test procedures that include instructions for testing hardware, software, capabilities, features, functionalities, or protocols of a computing device. Each code segment can encapsulate logic that, when executed, identifies whether a corresponding test procedure is applicable to a device given that device's configuration. By executing each code segment, a set of applicable test procedures can be identified. Identifiers or the test procedures may be provided to the device to be tested or a testing platform configured to conduct the test of that device. Transmitting the identifiers and/or procedures configures those devices to perform the test through simulating a legitimate data exchange.
A method for recurrent neural networks for asynchronous sequences may include receiving first input data associated with a plurality of first data items ordered in a first sequence and second input data associated with a plurality of second data items ordered in a second sequence. Each first data item may be of a first type, and each second data item may be of a second type. Each respective data item of the first and second data items may be inputted with an indicator associated with a respective type of the respective data item to a recurrent unit of a recurrent neural network (RNN). A respective portion of a hidden state may be determined based on the indicator. The respective portion of the hidden state may be updated based on the respective data item and the indicator. A system and computer program product are also disclosed.
A method is disclosed. It includes receiving, from a resource provider computer, an authorization request message comprising a credential or a token, and a value for an interaction, and transmitting the authorization request message comprising the credential, and the value to a first authorizing entity computer. The method includes receiving an authorization response message from the first authorizing entity computer, the authorization response message comprising an indication that the first authorizing entity computer is unable to provide an authorization decision on the authorization response message. The method includes determining that the credential is associated with a flagged record, and then generating a subsequent authorization request message comprising the credential or data associated with the credential, the value, and a record value of a record managed by the first authorizing entity computer.
Embodiments of the invention are directed to systems, methods, and devices for securely performing federated tasks (e.g., the generation and utilizing of machine-learning models). A secure platform computer may operate a secure memory space. Entities participating in a federated project may transmit respective portions of project data defining the federated project. Each entity may provide their respective (encrypted) data sets for the project that in turn can be used to generate a machine-learning model in accordance with the project data. The machine-learning model may be stored in the secure memory space and accessed through an interface provided by the secure platform computer. Utilizing the techniques discussed herein, a machine-learning models may be generated and access to these models may be restricted while protect each participant’s data set from being exposed to the other project participants.
Methods and systems for explaining the output of machine learning models using contribution values are described. In many applications, a complex machine learning model may be used to produce an output (e.g., a classification) or otherwise perform some analysis. However, due to its complexity, it may be difficult to generate explanations (e.g., relating the outputs of that machine learning model to its inputs) in a timely manner. In embodiments of the present disclosure, a lightweight surrogate model can be trained to generally copy the performance of a primary machine learning model. Explanations can be generated based on the outputs of the surrogate model, which can be used as surrogate explanations for the primary machine learning model. Such surrogate explanations can be generated more quickly due to the lesser complexity of the surrogate model, enabling such explanations to be used in real-time production environments.
A method is disclosed. The method includes receiving a transaction creation request for creating a transaction, the transaction creation request comprising transaction details. The method also includes determining a process value associated with processing the transaction, determining, using a plurality of factors, a relay storage application from a plurality of storage applications to process the transaction. The method also includes obtaining a counter value for the transaction, signing the transaction using a private key associated with the determined storage application; and transmitting the signed transaction and the counter value to a blockchain network managing a blockchain for inclusion in the blockchain.
G06Q 20/02 - Payment architectures, schemes or protocols involving a neutral third party, e.g. certification authority, notary or trusted third party [TTP]
In some embodiments, a method includes monitoring behavior patterns of a plurality of devices associated with a user in an authentication network; generating a behavioral accuracy score for each device of the plurality of devices in the authentication network based on the behavior patterns of each device of the plurality of devices; generating a deviation score for each device of the plurality of devices based on a deviation in behavior of each device of the plurality of devices from conventional device behavior; and using the behavioral accuracy score and the deviation score to determine whether to isolate a device of the plurality of devices from the authentication network. In some embodiments, the method further includes determining whether the behavioral accuracy score of a first device of the plurality of devices is within a first behavioral accuracy score category, a second behavioral accuracy score category, or a third behavioral accuracy score category.
Provided are methods for enhancing a distribution of graph feature embeddings in an embedding space to improve discrimination of graph features by a graph neural network (GNN) that may include receiving a dataset comprising graph data associated with a graph, calculating a distance between a first set of node embeddings and a second set of node embeddings, determining a measure of uniformity for the dataset, determining a plurality of groups of node embeddings, determining a measure of alignment for the plurality of groups of node embeddings, generating a set of graph features based on the measure of uniformity, the measure of alignment, and the distance, and training the GNN based on the set of graph features to provide a trained GNN. Systems and computer program products are also disclosed.
A method is disclosed. The method includes receiving, from a client device, a checkout request for a transaction between a user operating the client device and a resource provider operating the resource provider computer. The resource provider computer and the client device communicate via a first communication channel. The method includes obtaining a first one-time code, displaying, the first one-time code to the user on the client device, and determining an indication that the first one-time code matches a second one-time code that was provided by the user through a second communication channel that is different than the first communication channel. The method includes allowing the transaction to continue based on the determination that the first one-time code matches the second one-time code.
G06Q 20/12 - Payment architectures specially adapted for electronic shopping systems
G06Q 20/16 - Payments settled via telecommunication systems
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
74.
Method, System, and Computer Program Product for Multitask Learning on Time Series Data
Provided are methods for generating a multitask machine learning model based on time series data, that may include receiving input time series data associated with an input time series of data points, calculating a pairwise distance between the input time series and a plurality of time series templates, providing the pairwise distance as a first input to a building block of a residual neural network, where the residual neural network has a plurality of multi-dimensional convolutional layers; generating a first output of the first building block of the residual neural network based on the first input, generating a final output of the residual neural network based on the first output, and generating a first output of a multitask machine learning model using a first output layer and a second output of the multitask machine learning model using a second output layer. Systems and computer program products are also disclosed.
A method is disclosed. The method includes receiving, by an application on a communication device from an access device, a unique identifier associated with a resource provider in a transaction. The method also includes transmitting, by the application, a message comprising the unique identifier and an access data reference identifier associated with access data to a remote server computer associated with the application. The remote server computer searches a database for access data using the access data reference identifier, retrieves the access data, and provides the access data to a transport computer which processes the transaction using the access data.
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
A method includes receiving, by a service provider application on a communication device, a selection of a user device identifier to conduct an interaction from a user; presenting, by the service provider application, options for the user of the communication device to select an interaction type from a plurality of interaction types; receiving, by the service provider application, a selection of an interaction type from the user; presenting, by the service provider application, a plurality of addition methods associated with the interaction type, the plurality of addition methods associated with a data processing computer; receiving, by the service provider application, a selection of an addition method associated with the interaction type; and processing, by the communication device, the interaction type using the addition method and a token associated with the interaction type.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06Q 20/34 - Payment architectures, schemes or protocols characterised by the use of specific devices using cards, e.g. integrated circuit [IC] cards or magnetic cards
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
A method and system for provisioning credentials is disclosed. The method includes receiving, by a server computer from an authorizing entity computer, a provisioning request message. The provisioning request message can include resource provider identifiers for a set of resource providers and a set of credentials to be associated with the set of resource providers. The method further includes transmitting, by the server computer, a provisioning instruction message to an intermediate computer. The provisioning instruction message can include the resource provider identifiers and credential reference identifiers associated with the set of credentials. The intermediate computer can transmit one or more token request messages to a token service computer, receive tokens corresponding to the credential reference identifiers, and provision the tokens to the resource providers associated with the resource provider identifiers.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
78.
MERCHANT MERCHANT PRESENTED PAYMENT ACCEPTANCE CREDENTIAL (MPPAC) AUDIT VERIFICATION SYSTEM AND METHOD THEREFOR
In some embodiments, a system, includes a processor; and a non-transitory computer readable medium coupled to the processor, the non-transitory computer readable medium including code that: generates, at a payment network, a payment-network-generated Merchant Presented Payment Acceptance Credential (MPPAC), the payment-network-generated MPPAC being configured to be utilized in a merchant MPPAC audit of a merchant; provides the payment-network-generated MPPAC to the merchant for use in the merchant MPPAC audit; receives, at the payment network, a merchant-captured MPPAC, the merchant-captured MPPAC having been captured by the merchant for a merchant MPPAC audit verification; and utilizes, at the payment network, the payment-network-generated MPPAC and the merchant-captured MPPAC to perform the merchant MPPAC audit verification.
A method is disclosed. The method includes receiving, by an electric vehicle, a list of available services associated with an electricity supply terminal. The list of available services includes one or more methods that do not transmit credentials or tokens via a charging cable and one or more methods that do transmit credentials or tokens via the charging cable. The method also includes determining, by the electric vehicle, a set of services in the list of available services. The set of services includes services supported by the electric vehicle. The method also includes transmitting, by the electric vehicle to the electricity supply terminal, a service selection request comprising a service in the set of services. The method also includes receiving, by the electric vehicle from the electricity supply terminal via the charging cable, electricity from the electricity supply terminal.
Embodiments of the present disclosure enable users to efficiently verify digital data produced by queried databases, even when that data is differentially-private (e.g., satisfying the conditions of differential privacy in order to protect sensitive or private data). In addition to the query result, a database computer can provide the client with a non-interactive zero-knowledge proof (NIZK), data that the client can use to verify the digital data contained in the query result, without revealing any private data to the client. Various innovations, including vectorized proofs, enable the database computer to generate proofs that require less data (e.g., when measured in bytes) than most NIZK proof systems. Consequently, these proofs can be transmitted and verified more quickly and efficiently. Embodiments of the present disclosure can make use of partially or homomorphic commitments and efficient vector proof techniques to achieve these performance improvements.
A method is disclosed. The method includes transmitting a verification request comprising a wallet account identifier associated with a digital wallet to a smart contract on a blockchain network or a smart contract application associated with the smart contract. The smart contract or the smart contract application verifies the wallet account identifier using a blockchain on the blockchain network. The method also includes receiving from the smart contract on the blockchain network or the smart contract application, a verification response verifying the wallet account. The method further includes initiating transmitting to an authorizing entity computer, an authorization request message comprising a credential associated with the wallet account identifier.
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
82.
AUTHENTICATION WITH RELYING PARTY AND AUTHENTICATING PARTY
A computer receives a credential and a user device identifier from a relying party computer. The computer determines whether or not a token related to the user device identifier exists and determines whether or not the credential is associated with a cryptographic authentication process. The computer provides a status message indicating whether or not the credential is associated with the cryptographic authentication process to the relying party computer. Based on the status message, the computer receives a challenge request message from the relying party computer. The computer generates a challenge and provides the challenge to a user device via the relying party computer or to the user device. The user device performs an authentication process in response to the challenge and provides an authentication assertion to the computer directly or via the relying party computer. The computer verifies the authentication assertion and provides authentication results to an authorizing entity computer.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
41 - Education, entertainment, sporting and cultural services
Goods & Services
Streaming of audio, video and multimedia content via the Internet; video-on-demand transmission services; electronic transmission of data, messages and information; providing access to online platforms, portals and databases; providing online forums and communication platforms for discussion and collaboration in the field of artificial intelligence; transmission of data in the field of artificial intelligence and software development; providing access to collaborative online environments; telecommunication services for enabling interaction between users in digital learning environments in the field of artificial intelligence. Education and training services in the field of artificial intelligence and machine learning; organization of courses, workshops, seminars, conferences, competitions and training events in the field of artificial intelligence; providing online non-downloadable courses and tutorials in the field of artificial intelligence; publication of educational materials in the field of artificial intelligence; providing online trainings featuring non-downloadable educational content in the field of artificial intelligence, production of educational audio and video content in the field of artificial intelligence; providing online certification programs in the field of artificial intelligence; coaching services in the field of artificial intelligence and digital technologies; publishing of digital content, namely articles, guides and instructional materials in the field of artificial intelligence; entertainment services, namely provision of non-downloadable music, including AI-generated music.
84.
CONFIGURATION OF NODE PORT FOR MAINTENANCE WITHOUT LOAD BALANCER COORDINATION
A computer implemented method providing a network policy configured to prevent transaction data processing from being interrupted during maintenance performed on nodes in a cluster network. The network policy reduces maintenance period times and the amount of personnel needed to perform node maintenance by simulating node failure. The simulated node failure prevents new transaction data from being sent the node that is undergoing maintenance.
H04L 41/0668 - Management of faults, events, alarms or notifications using network fault recovery by dynamic selection of recovery network elements, e.g. replacement by the most appropriate element after failure
Methods, systems, and computer program products are provided for shared latent space-based debiasing. An example system includes at least one processor configured to: transform data from each of a target domain, which lacks protected features, and a separate source domain, which contains these features, into correlated latent representations; jointly train a cross-domain protected group estimator on the representations; and debias a downstream machine learning model an adversarial learning technique that leverages the group estimator.
Embodiments of the present disclosure are directed to the methods and systems for generating artificial data records from (potentially private or sensitive) data records in a privacy-preserving manner, particularly using machine learning models such as generative adversarial networks (GANs). Such artificial data records can be used in place of the real data in data analysis applications, such as training machine learning models. These artificial data records can be generated such that they do not (or have a low or negligible probability of) leaking information from the data records used to generate the artificial data records. As a result, artificial data records (or any machine learning models trained to generate such artificial data records) can potentially be published or distributed without violating rules, regulations, or laws restricting the transmission of sensitive data.
A method is disclosed. The method includes receiving, from a user device storing a private key of a public-private key pair, a first attestation message comprising a first attestation data packet, the public key, a user device identifier for the user device, and a credential. The method also includes binding the credential to the user device identifier, and transmitting, to a token service computer, the first attestation data packet. The token service computer previously bound a first token from a first token requestor interacting with the user device to the user device identifier. The method includes receiving, from a second token requestor interacting with the user device, a second attestation message comprising a second attestation data packet, verifying, the second attestation data packet using the public key, and transmitting, verification data to the second token requestor. The second token requestor transmits the verification data to the token service computer.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
A method may be performed using a multi-stage framework with multiple large language model based agents. The method may comprise obtaining a query and retrieving a plurality of candidate documents from one or more data sources based on the query. A first language model agent can generate, for each candidate document of the plurality of candidate documents, an initial response to the query using the respective candidate document, thereby producing a set of document-query-response triplets. A second language model agent can evaluate, for each document-query-response triplet of the set of document-query-response triplets, a relevance of the initial response based on the respective candidate document. A subset of the candidate documents can be selected based on the relevance for each of the plurality of candidate documents. A third language model agent can generate a response to the query using the subset of candidate documents.
The present disclosure provides various cards (e.g., payment cards, identification cards, driver's license cards) that are removably attachable to a portable electronic device. In some aspects, the portable electronic device may include a charging coil, a ferromagnetic component disposed about the charging coil, and a ferromagnetic alignment component. The card can include a substrate and a magnet embedded the substrate. The magnet can magnetically couple to the ferromagnetic component disposed about the charging coil.
G06K 19/077 - Constructional details, e.g. mounting of circuits in the carrier
G06K 19/07 - Record carriers with conductive marks, printed circuits or semiconductor circuit elements, e.g. credit or identity cards with integrated circuit chips
Systems and methods for low communication distributed systems are disclosed. An example method can comprise receiving, by each node in a distributed system, a correlation function with a plurality of inputs comprising at least an identifier; receiving, at a node of the distributed system, a request comprising the identifier; identifying, by the node, a service node to serve the request based on the correlation function, the identifying comprising determining, by the node, based on a status of the node, the status of other nodes in the distributed system; determining a local state, based on at least one of the status of the node, the status of the other nodes, or a number of nodes in the distributed system; and calculating, based on the local state and the plurality of inputs, a target response that identifies the service node; and processing the request by the service node.
G06Q 20/02 - Payment architectures, schemes or protocols involving a neutral third party, e.g. certification authority, notary or trusted third party [TTP]
H04L 12/18 - Arrangements for providing special services to substations for broadcast or conference
Systems and methods for entity linking using a graph neural network are disclosed. In one aspect, a method for entity linking can include extracting a first attribute set of an unknown entity from an information source and retrieving second attribute sets of known entities from a database, wherein each of the second attribute sets corresponds to one of the known entities. The method can further include generating an unknown entity graph based on the first attribute set, generating known entity graphs based on the second attribute sets, generating an unknown entity graph embedding by applying the unknown entity graph to a graph neural network, and generating known entity graph embeddings by applying the known entity graphs to the graph neural network. The method can further include assigning the information source to one of the known entities based on the unknown entity graph embedding and the known entity graph embeddings.
Systems, methods, and computer program products for reducing order bias of machine learning models via feature re-ordering are provided. An example system may include a processor to receive a training dataset comprising a plurality of data instances for a plurality of features, generate a feature trajectory of the plurality of features based on an output of a critic machine learning model, wherein the output of the critic machine learning model comprises a prediction of a value of loss of an output of a large language model (LLM), estimate a value of loss of an output of the LLM based on the feature trajectory to provide an estimated value of loss, update one or more parameters of the critic machine learning model to minimize the estimated value to provide an updated critic machine learning model, and generate a final output using the updated critic machine learning model.
Embodiments of the invention provide methods for conducting an interaction between a user device and an access device to initiate a transaction based on a user-selected application. The user can present their user device to an access device, and the user device can interact with the access device to transmit a set of application identifiers and corresponding credentials to the access device. The access device can prompt the user to select an application via a user interface of the access device for use in the transaction. The access device can then process the transaction based on the selected application.
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
41 - Education, entertainment, sporting and cultural services
42 - Scientific, technological and industrial services, research and design
Goods & Services
educational services, namely, providing courses, workshops, and seminars in the field of building AI-native applications for use in financial payment processing and transaction services; entertainment services, namely, providing online content in the nature of online non downloadable videos featuring AI-generated music and AI-centered educational programming in the nature of online non downloadable educational videos in the field of financial payment processing and transaction services providing online, non-downloadable software development tools for use in training individuals to build AI-native software applications specifically for use in financial payment processing and transaction services
96.
System, Method, and Computer Program Product For Deep Learning With Plausible Deniability
Systems, methods, and computer program products are provided for deep learning with plausible deniability. An example system includes at least one processor configured to: (i) obtain a dataset including a plurality of batches of data samples; (ii) compute a plurality of gradients of the plurality of batches; (iii) select a gradient; (iv) add noise to the selected gradient; (v) determine, based on the noised gradient and the plurality of gradients, a number of gradients that satisfy a privacy function; (vi) in response to the number of gradients that satisfy the privacy function satisfying a threshold number, training, using the noised gradient, a machine learning model; and (vii) in response to the number of gradients that satisfy the privacy function failing to satisfy the threshold number, reshuffling the dataset to generate an updated plurality of batches of data samples and returning to step (ii).
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
97.
SYSTEM, METHOD, AND COMPUTER PROGRAM PRODUCT FOR IMPROVED MODEL TRAINING USING REINFORCEMENT LEARNING AND FEATURE DROPOUT
Systems, methods, and computer program products are provided for improved model training using reinforcement learning and feature dropout. An example system includes at least one processor configured to receive a pretrained machine learning model, which includes a first input layer and first hidden layers and has been trained based on training data including data records, each including a plurality of features. A second machine learning model is initialized and includes a second input layer, a feature selection layer, and second hidden layers. The second input layer and second hidden layers are initialized based on the first input layer and the first plurality of hidden layers, respectively. The feature selection layer includes weights including a respective weight for each respective feature. Each weight is associated with a dropout rate for the respective feature. The weights are adjusted based on the training data and at least one reinforcement learning reward.
Systems, methods, and computer program products for dynamic optimization of complex SQL queries in data lakehouse query engines are provided. An example system may include at least one processor configured to receive data associated with operations of computational resources of a computer cluster receive data associated with a query to be carried out by the computer cluster during a time interval, provide an input to a cluster load machine learning model to generate an output of the cluster load machine learning model, where the output comprises a prediction of load on the computer cluster during the time interval, determine to adjust at least one session parameter associated with the query, and adjust the at least one session parameter associated with the query based on determining to adjust the at least one session parameter associated with the query.
A computer system automates and balance loads balancing a Highly Available Server (HA server), a plurality of nodes, a final delivery server, a failover mechanism within the HA server, and a methodology for a reinforcement learning model. The HA server maintains a dynamic list of reports, assigns tasks to the nodes based on their availability status, and employs a reinforcement learning-based model to optimize task assignment. The nodes receive and complete assigned tasks from the HA server and sends task outputs back to the HA server. The final delivery server receives processed reports from the HA server. The failover mechanism detects node failures and reassigns tasks among remaining operational nodes. The reinforcement learning model updates its task allocation policy based on the success or failure of completed tasks, maximizes system efficiency, and adjusts the policy to mitigate the impact of system failures.
Methods, systems, and machine learning models for efficiently performing time series forecasting for multivariate time series datasets are disclosed, particularly multivariate time series datasets that comprise a large number of variates (or "time series signals") and for which time series signals may emerge and disappear over the sampling time period. A computer system according to embodiments can generate signal embeddings corresponding to time series signals in a multivariate time series dataset and use an efficient (e.g., linear) latent attention module to generate an attention matrix. The computer system can then generate a time series forecast using the attention matrix and a forecasting model. Methods according to embodiments can also involve the use of random projection, reducing the risk of overfitting and improving accuracy for large and complex spatial-temporal datasets.
