Abstract: A model evaluation system evaluates the extent to which privacy-aware training processes affect the direction of training gradients for groups. A modified differential-privacy (“DP”) training process provides per-sample gradient adjustments with parameters that may be adaptively modified for different data batches. Per-sample gradients are modified with respect to a reference bound and a clipping bound. A scaling factor may be determined for each per-sample gradient based on the higher of the reference bound or a magnitude of the per-sample gradient. Per-sample gradients may then be adjusted based on a ratio of the clipping bound to the scaling factor. A relative privacy cost between groups may be determined as excess training risk based on a difference in group gradient direction relative to an unadjusted batch gradient and the adjusted batch gradient according to the privacy-aware training.

Abstract: According to an aspect there is provided an ambient commerce system. The ambient commerce system may include a sensor at an ambient commerce premises, a communication module, and a processor coupled to the sensor and the communication module. The ambient commerce system further includes a memory coupled to the processor. The memory stores processor-executable instructions which, when executed, cause the processor to: detect, based on an output of one or more of the sensors, an unauthenticated entity at an ambient commerce premises; receive, from a first independent trusted system and via the communication module, an indication that authentication has been performed by the first independent trusted system for the unauthenticated entity using a first authentication parameter; determine that the entity is an authenticated entity based on the indication that the authentication has been performed and at least a second authentication parameter; and perform an ambient commerce operation for the authenticated entity.

Abstract: Probability density modeling, such as for generative modeling, for data on a manifold of a high-dimensional space is performed with an implicitly-defined manifold such that points belonging to the manifold is the zero set of a manifold-defining function. An energy function is trained to learn an energy function that, evaluated on the manifold, describes a probability density for the manifold. As such, the relevant portions of the energy function are “filtered through” the defined manifold for training and in application. The combined energy function and manifold-defining function provide an “energy-based implicit manifold” that can more effectively model probability densities of a manifold in the high-dimensional space. As the manifold-defining function and the energy function are defined across the high-dimensional space, they may more effectively learn geometries and avoid distortions due to change in dimension that occur for models that model the manifold in a lower-dimensional space.

Abstract: A computer-implemented method is disclosed.

Abstract: A computer server system comprises a communications module; a processor coupled with the communications module; and a memory coupled to the processor and storing processor-executable instructions which, when executed by the processor, configure the processor to receive, via the communications module and from a requesting device, a signal that includes a request to send a stored-value card to a recipient, the request identifying one or more parameters of the stored-value card; generate the stored-value card and a three-dimensional object representing the stored-value card according to the one or more parameters; and send, via the communications module and to a mobile device of the recipient, a signal that includes the three-dimensional object representing the stored-value card for display in augmented reality.

Abstract: A system and method are provided for persisting data generated in executing a process workflow. The method is executed by a device having a communications module and includes receiving via the communications module messages exchanged in executing the process workflow by a message broker. The method also includes using a writer service to disassemble each received message into multiple properties according to a database schema and persist the received message in a database according to the database schema via the communications module. The method also includes using a reader service to access the database and assemble the multiple properties of a first persisted message, in response to a read request received via the communications module, wherein the reader service is separate from the writer service.

Abstract: Systems and methods of determining whether to initiate a pull of an accumulated data transfer amount are described. An accumulated data transfer amount for a periodic data transfer scheduled to be pushed at a future date is determined. A determination is made of whether an overall data amount in a storage location is expected to be greater at a date on or after the scheduled future date if a pull of the accumulated data transfer amount is performed before the scheduled future date than if a pull operation is not performed and the accumulated data transfer amount is sent at the scheduled future date. When the overall data amount in the storage location is expected to be greater at the scheduled future date if the pull of the accumulated data transfer amount is performed, a pull of the accumulated data transfer amount is initiated.

Abstract: An example operation may include one or more of receiving, via a host platform, a payment authorization request message for a payment transaction of a digital wallet hosted by the host platform from a payment gateway of an electronic payment network, verifying that a payment account in the digital wallet has sufficient funds to satisfy an amount of the payment transaction and transmitting a payment authorization response to the payment gateway, pausing clearing and settling of the authorized payment transaction, executing a blockchain transaction via a blockchain ledger of a cryptocurrency network to exchange fiat currency from the payment account for cryptocurrency based on the amount of the payment transaction, prior to a due date of the authorized payment transaction, executing a second blockchain transaction to exchange the cryptocurrency for a new amount of fiat currency, and settling the authorized payment transaction based on the new amount of fiat currency received from the second blockchain transacti

Abstract: An example operation may include one or more of receiving, via a host platform of a digital wallet, a payment authorization request message for a payment transaction of the digital wallet from a payment gateway of an electronic payment network, verifying that the digital wallet has sufficient funds to satisfy an amount of the payment transaction and transmitting a payment authorization response to the payment gateway, pausing clearing and settling of the authorized payment transaction, generating an entry that represents the authorized payment transaction and storing the entry in a temporary storage structure of the host platform, executing a cryptocurrency transaction which exchanges cryptocurrency for an amount of fiat currency that satisfies the amount of the payment transaction, and canceling the authorized payment transaction and settling the payment transaction based on the amount of fiat currency received from the cryptocurrency transaction.

Abstract: A computer-implemented method for allowing purchase of virtual gift cards includes receiving a communication indicating a gift card type and specifying a value amount. Responsive to the communication, a purchase of a virtual gift card of that type and storing that value amount is processed. This processing includes processing a payment for the specified value amount. Further, a gift card merchant application programming interface (API) capable of processing a purchase of a virtual gift card of the indicated gift card type is identified from amongst a set of such APIs. That API is used to initiate purchase of the virtual gift card. After the purchase is processed, an indication of the purchased virtual gift card is sent to a mobile computing device. The mobile computing device uses the indication to configure itself to allow transactions using the purchased virtual gift card to be initiated. Fraud detection may also be performed.

Abstract: A server computer system, comprises a processor; a communications module coupled to the processor; and a memory coupled to the processor, the memory storing instructions that, when executed, configure the processor to receive, via the communications module and from a client device, a signal including a request to configure a transfer of data to a particular data record; determine that the particular data record is associated with a third party server; obtain a trust score associated with the particular data record; determine that the trust score satisfies trust criteria; and responsive to determining that the trust score satisfies trust criteria, enable one or more transfer features associated with a real-time transfer protocol.

Abstract: In an aspect, the present application describes a computer system. The computer system includes a communications module and a processor coupled to the communications module. The computer system include a memory coupled to the processor storing instructions that, when executed by the computer system, cause the computer system to: receive, from an automated teller machine (ATM) and via the communications module, an indication of a deposit of a value instrument; save, in the memory, a retention instruction including an associated temporal period, the retention instruction preventing withdrawal of value instruments corresponding to an amount of the deposit; receive, via the communications module, an instruction to process a data transfer to a recipient, the data transfer to the recipient accessing at least a portion of the deposit; and process the data transfer to the recipient during the temporal period using at least a portion of the deposit.

Abstract: A server comprises a communications module; a processor coupled with the communications module; and a memory coupled to the processor and storing processor-executable instructions which, when executed by the processor, configure the processor to send, via the communications module and to a remote computing device, a signal causing the remote computing device to display a unique code and a telephone number; monitor at least one instant messaging account associated with the telephone number for the unique code; after determining that the unique code has been received at the at least one instant messaging account associated with the displayed telephone number, determine that authentication for a particular account has been successful; and in response to determining that authentication for the particular account has been successful, initiate an authenticated session.

Abstract: A computer system for automatically handling and releasing funds for deposit items has a memory storing instructions that, when executed by a processor, cause the system to receive an image of a cheque received and scanned by an automated teller machine (ATM) for deposit into a first account of an institution associated with the ATM. The scanned image of the cheque is analyzed to identify an institution and account on which that cheque is drawn. If that account has sufficient available funds to cover the cheque, then the first account is credited in the amount of the cheque without placing a hold on any of the credited amount and funds of the account on which the cheque is drawn are encumbered in that same amount. After crediting the first account, an indication is provided that the funds are available (e.g., to withdraw). Related methods and computer-readable media are also disclosed.

Abstract: A computer-implemented method is disclosed.

Abstract: The disclosed exemplary embodiments include computer-implemented systems, devices, and processes that securely distribute digital assets within a computing environment using permissioned distributed ledgers. For example, an apparatus may receive, from a computing system, an allocation request, a first digital signature applied to the allocation request, and a second digital signature applied to the allocation request and to the first digital signature. Based on a validation of the first and second digital signatures, the apparatus may approve the allocation request and allocate a digital asset to the first device in accordance with the approved allocation request. The apparatus may also perform operations that record a public key and asset data identifying a digital asset onto a distributed ledger, and may generate and transmit, to the first device, confirmation data indicative of the allocation of the digital asset to the first device.

Abstract: A computer-implemented method is disclosed. The method includes: receiving, via a communication interface from a client application executing on a first device, a first signal including a request to obtain an access token for accessing a protected resource, the request including a public key associated with an end user; validating the request to obtain the access token; and in response to validating the request: encrypting an authorization code associated with the request using the public key to generate a first code; and transmitting, via the communication interface to the client application on the first device, a second signal including both the access token for accessing the protected resource and the first code.

Abstract: A content retrieval system uses a graph neural network architecture to determine images relevant to an image designated in a query. The graph neural network learns a new descriptor space that can be used to map images in the repository to image descriptors and the query image to a query descriptor. The image descriptors characterize the images in the repository as vectors in the descriptor space, and the query descriptor characterizes the query image as a vector in the descriptor space. The content retrieval system obtains the query result by identifying a set of relevant images associated with image descriptors having above a similarity threshold with the query descriptor.

Abstract: The disclosed exemplary embodiments include computer-implemented systems, apparatuses, and processes that dynamically and securely augment a programmatically established communications session, such as a chatbot session, to include one or more additional responsive applications. For example, an apparatus may receive messaging data during a first communication session programmatically established between a device and a first executed application program, and may determine that an additional apparatus is configured to perform operations consistent with the messaging data. The apparatus may transmit a digital token and at least a portion of the messaging data to an additional apparatus. A second application executed by the additional apparatus may validate the digital token and based on the portion of the messaging data, establish a second communication session between the device and the executed first and second application programs.

Abstract: The disclosed embodiments include computer-implemented processes that predict a credit score for a customer in real-time based on an application of a trained machine-learning or artificial-intelligence process to encrypted event data at a third-party computing cluster. For example, an apparatus may transmit encrypted event data to a third-party computing system. The third-party computing system may apply a trained artificial intelligence process to encrypted feature data that includes the encrypted event data, and the apparatus may receive, from the third-party computing system, encrypted output data representative of a predicted credit score during at least one temporal interval. The apparatus may decrypt the encrypted output data using a homomorphic decryption key, and transmit a notification that includes the decrypted output data to a device. An application program executed at the device may present a graphical representation of at least a portion of the decrypted output data within a digital interface.