Abstract: A method and apparatus for performing privacy preserving fraud detection in network based transactions are described. The method may include receiving a fraud detection message during a transaction between a user system and a merchant system, the message having a set of cryptographically transformed universal resource locator (URL) components generated from a URL of a web page of the merchant system on which the transaction is to occur. The method may also include generating one or more secure and anonymous fraud detection features, each fraud detection feature comprising a select subset of the cryptographically transformed URL components. The method may also include performing fraud detection for the web page using the one or more secure and anonymous fraud detection features to determine a likelihood that fraud is occurring in the transaction.

Abstract: A user scans a payment card while setting up an account on a merchant's website, or while completing a check out to purchase an item or service for the first time. The subject system stores signals from the card scan (e.g., device ID, verified card, location, last time scanned and used, etc.). The next time a transaction is requested for the card at another merchant, the subject system can reference the last data it has on the card. If the transaction is being requested from the same device or a reasonably close physical location within a reasonable timeframe, the subject system can be highly confident that this is a legitimate transaction, without requiring the customer to scan their payment card again.

Abstract: A method is disclosed for assessing the health of a cluster within a distributed data storage system. The method involves a first service receiving a request related to the health status of a cluster. The first service validates the received request. A second service transmits a message to the first service to obtain data associated with the cluster. The second service receives the requested data from the first service. Based on the received data and through communication with the cluster, the second service determines the health of the cluster.

Abstract: Presented herein are systems and methods of training machine learning (ML) models to determine likelihoods of fraud in network operations caused by computing systems. A server may generate training data to include (i) a digital fingerprint associated with an identity of a computing system of a plurality of computing systems and (ii) a plurality of network operation metrics associated with the computing system. The server may label the training data to indicate whether fraudulence is caused by the computing system. The server may execute, using the training data, a ML model having a plurality of weights to generate a likelihood of fraud caused by the computing system. The server may compare the likelihood of fraud with labeled training data to determine an error metric in accordance with a loss function. The server may update at least one of the plurality of weights using the error metric.

Abstract: Disclosed herein are methods and systems for improved service system configuration during distributed services execution by a distributed services system. In one example, different sets of machine learning models respectively generate signals indicative of predicted risk and expected values associated with execution of a service by the distributed services system. Next, expected values associated with actions, where each action corresponds to a configuration of the service, are determined so that an action that maximizes the expected value associated with the execution of the service based on the predicted risk can be selected. The action is then executed configuring the execution of the service for a user in the distributed services system.

Abstract: A method and apparatus for updating data router nodes in a distributed storage system are described. The method can include querying, by a first database agent of a database node, a cache data store for health status metrics of the cache data store. The method can also include storing, by the first database agent of the database node, the health status metrics in a data repository. Furthermore, the method can include obtaining, by a second database agent of a router node, the health status metrics from the data repository, and updating, by the second database agent of the router node, a database topology file based on the health status metrics.

Abstract: A machine learning framework and method for using the same are described.

Abstract: A method and apparatus for executing a service of a server computer system for a client system are described. The method may include defining a client system descriptor file that includes a set of signals suitable for input into a large language machine learning model (LLM), and collecting data associated with a first client system that is representative of the set of signals. The data can then be compressed into the set of signals for a first client system descriptor file allocated for the client system. A query is executed using at least the first client system descriptor file as input into the LLM, and in response to an output obtained by the LLM, at least an action is executed by the service of the server computer system.

Abstract: Presented herein are systems and methods of generating embeddings for network events to detect fraudulent activities in networked environments. A service may receive a request to execute a first network operation in a network environment. The service may identify an event dataset associated with the first network operation to be executed. The service may apply the first event dataset to a machine learning (ML) model comprising a plurality of weights. The ML model may be established using training data comprising (i) a first sample event dataset associated with a second network operation and (ii) a second sample event dataset corresponding to a modification of a portion of the first sample event dataset. The service may generate, based on applying the event dataset of the first network operation to the ML model, a plurality of embeddings indicative of fraudulence of the first network operation.

Abstract: Methods and systems for disambiguating a user from a plurality of users within a computing infrastructure when the plurality of users utilize a common identifier are described. Disambiguation may occur through the user of subsequent verification of the identity of the user which generates an authentication token to be passed to the computing infrastructure during authentication requests using the common identifier.

Abstract: Disclosed herein are systems and methods for identifying and transmitting electronic requests to a suitable service provider. In one method, a server receives, from a computing device, a request to verify data via at least one service provider; executes a first computer model to identify a likelihood of verification success of the data; responsive to the likelihood of verification success satisfying a threshold, executes a second computer model to determine a service provider to transmit the request based on a first attribute associated with the data, a type of verification associated with the request, and a second attribute associated with the set of service providers and an impact value associated with each service provider; and responsive to determining the service provider from the set of service providers, transmitting, by the processor via an application programming interface, the data to the service provider.

Abstract: Various embodiments include systems, methods, and non-transitory computer-readable media for managing access control. Consistent with these embodiments, a method includes receiving a request to access a resource, determining one or more access control policies that correspond to an access to the resource; identifying an access control policy that allows the identity to access the resource, determining, that the identified access control policy is associated with a policy evaluation mode, and authorizing the request based on the access control policy.

Abstract: A method includes: receiving an initial input message from a caller to a processing system configured to receive input messages and to generate output messages in response to the input message and a persistent store; identifying a workflow associated with the initial input message, the workflow including activities, each activity being separately classified as an idempotent read-write activity, an idempotent read-only activity, or a non-idempotent read-only activity associated with a corresponding service of the processing system; and executing the workflow by supplying the initial input message to the workflow and, for each activity: in response to determining that an input message to the activity includes non-reproducible data, storing the non-reproducible data in the persistent store only if the input message includes non-reproducible data and the activity is a read-write activity or a return to the caller; and providing the input message to a service corresponding to the activity.

Abstract: A method and apparatus for authentication of a user is described. A system can include a memory and a processor, where the processor identifies a trigger event corresponding to an application executed by the processor of the system. Then, in response to identification of the trigger event, the processor causes an authentication process to execute on the application, including prompting the user to provide a payment instrument information via the NFC device of the system. The processor then determines if the received payment instrument information is designated as an authentication instrument for the user, in response to receipt of the payment instrument information via the NFC device of the system, determine. Additionally, in response to a determination that the received payment instrument information is designated as the authentication instrument for the user, the processor authenticates the user.

Abstract: A client-side method facilitates secure transactions between a customer and a merchant by isolating sensitive payment information from the merchant's systems. A payment form displayed on an electronic device receives payment data and, upon loading, establishes a secure communication tunnel with a third-party server for cross-origin communication. When the form is submitted, an event handler intercepts the submission and transmits the payment information through the secure tunnel to the third-party server, where the information is converted into a token. The token, representing the payment information, is returned via the secure tunnel and provided to a merchant server along with other form data, excluding the underlying payment information, thereby enabling transaction processing while reducing exposure of sensitive data.

Abstract: A method and apparatus validating integrity of an environment of a terminal device remote to a commerce platform system are described. The method can include receiving, from the terminal device, a device provisioning request that comprises data indicative of an instance of an application installed on the terminal device, a first public key, a second public key, and a hardware attestation key, the first public key, the second public key, and the hardware attestation key generated within a trusted execution environment of the terminal device, and the first public key and the second public key having a corresponding first private key and second private key stored within the trusted execution environment.

Abstract: Aspects of the subject technology provide for synchronization between a first database and a second database. When a repeated command to a second database for a write operation to the second database is not performed, a forward synchronization process can update records from the first database to the second database. A reverse synchronization process can be used to further check that the synchronization is complete.

Abstract: Disclosed herein are systems and methods for monitoring network traffic to identify cyberattacks. An example method includes obtaining a first plurality of data packets transmitted over a network during at least one period of time; determining a plurality of feature values based on the plurality of data packets, each feature corresponding to execution of a protocol by the first system; generating an embedding based on the plurality of feature values and an encoder, the encoder configured to generate embeddings based on pluralities of feature values, the embeddings corresponding to a period of time; and determining that at least one data packet of the plurality of data packets is involved in a cyberattack based on the embedding. The method can include causing an execution of a remedial protocol in association with the first system.

Abstract: Some embodiments involve systems and methods for facilitating authentication for an entity system to use a partner system using pooled identifiers (e.g., without requiring the entity system to first register with the partner system). In some embodiments, based on (i) a request, from a first entity system, indicating a first partner system to process at least a part of an operation and (ii) an indication that the first entity system is not registered for use of the first partner system, a platform system may link a first authentication identifier of the first identifier set with the first entity system. The platform system may process the operation using the first authentication identifier linked by the platform system with the first entity system, and the platform system may use platform authentication data established with the first partner system to authenticate the platform system to the first partner system for performing the operation.

Abstract: A server computer system for detecting a fraudulent electronic transaction may be configured to receive a transaction associated with a merchant. The system processes the transaction with a first machine learning model that is trained specific to the merchant, to obtain a first fraud detection, and processes the transaction with a second machine learning model that is trained based on a plurality of merchants, to obtain a second fraud detection. The system detects fraud associated with the transaction based on the first fraud detection and the second fraud detection. In response to detecting the fraud that is associated with the transaction, the system blocks the transaction.