An example computing device is programmed to: (a) detect an attempt to secondarily access a user account, the user account being involved in an ongoing primary financial session with a primary device; (b) raise the level of authentication required to secondarily access the user account beyond that which was required to access the account for the primary financial session; (c) when successful authentication at the raised level is achieved, permit secondary access to the user account through a secondary financial session and compare one or more user activities occurring during the secondary financial session to a plurality of fraud profiles; and (d) indicate fraud when comparison of the user activity is consistent with one or more of the plurality of fraud profiles.

A system and computer-implemented method for authenticating digital transactions. The method includes receiving a device registration request and a device attestation response including at least a device integrity status from a device. In response to the device registration request, the method includes providing a device registration response to the device, based on validation of the device integrity status. Further, the method includes receiving a first payment transaction request and an enrolment request from the device via an application to authenticate a second payment transaction request using a first type of authentication technique. Finally, the method includes enrolling the device to the first type of authentication technique and providing a second token to the device based on a result of the first payment transaction request, wherein the second token is used for authenticating the second payment transaction request.

Methods and systems are presented for assessing a veracity of device attributes obtained from a computer device based on estimating a number of processing cycles used by the computer device to perform a particular function. In response to receiving a transaction request from the computer device, software programming instructions are transmitted to the computer device for obtaining device attributes of the computer device. The software programming instructions may also include code that estimate a number of processing cycles used by the computer to perform a particular function. The particular function may be associated with obtaining at least one of the device attributes of the computer device. The estimated number of processing cycles may be compared against a benchmark profile. A risk associated with the transaction request is determined based on the comparing.

Embodiments of the present invention provide an improvement to conventional machine model training techniques by providing an innovative system, method and computer program product for the generation of synthetic data using an iterative process that incorporates multiple machine learning models and neural network approaches. A collaborative system for receiving data and continuously analyzing the data to determine emerging patterns is provided. The proposed invention involves generating synthetic data clusters to be stored and used for retraining the main model as well as other models. In addition, the invention includes using one or more (subset) of the synthetic data clusters to train or retrain machine learning models, developing and training machine learning models that are trained with emerging synthetic data clusters, and ensembling machine learning models trained with emerging synthetic data clusters.

Systems and methods for account validation are disclosed. A method may include: receiving, at a validation computer program and from a client device, a request to validate payment information; querying, by the validation computer program, a plurality of validation systems with at least some of the payment information; receiving, at the validation computer program, a query response from each validation system; calculating, by the validation computer program, a risk score for each validation system based on a comparison between the payment information and the query response; weighting, by the validation computer program, the risk score for each validation system, wherein the weighting may be based on an accuracy of past risk scores for each validation system; aggregating, by the validation computer program, the weighted risk scores into a cumulative risk score; and outputting the cumulative risk score to the client device.

A system includes a plurality of graph convolutional networks corresponding to a plurality of time steps, each network modelling a graph including nodes and edges, and in turn including a plurality of graph convolution units; an evolving mechanism; and an output layer. Each of the units, for a given one of the time steps, takes as input a graph adjacency matrix, a node feature matrix, and a parameter matrix for a current layer, and outputs a new node feature matrix for a next highest layer. The mechanism takes as input a parameter matrix for a prior time step updates the input parameter matrix, and outputs the parameter matrix for the given time step. The output layer obtains, as input, output of each of the units for a final time step, and based on the output of each of the units for the final time step, outputs a graph solution.

The disclosed computer-implemented method for proactive call spam/scam protection may include intercepting network traffic by the at least one processor employing a network extension feature of an operating system of a computing device. The method may additionally include capturing, by the at least one processor employing the network extension feature, a phone number in the network traffic. The method may also include comparing, by the at least one processor employing the network extension feature, the phone number to a plurality of entries in a spam/scam repository. The method may further include performing, by the at least one processor, a security action in response to the comparison. Various other methods, systems, and computer-readable media are also disclosed.

A system for decentralized private blockchains network is provided. In some implementations, the system performs operations comprising receiving, at a client system, data having a sensitivity level, the operations further comprise splitting, at the client system, the data based on the sensitivity level, the splitting comprising splitting the data into data portions. The operations further comprise storing, at a decentralized storage system, the decentralized storage system comprising a plurality of private blockchains, each of the data portions in a separate private blockchain of the plurality of private blockchains. The operations further comprise storing, at a multi-decentralized private blockchains network (MDDV), pointers to locations of the data portions within the decentralized storage system. Related systems, methods, and articles of manufacture are also described.

Embodiments relate to a system, program product, and method for automatically executing an impact analysis of a data analytics pipeline to determine impacts to the pipeline subject to changes to input data and the pipeline. The method includes determining, automatically, components of the pipeline that are impacted by the implemented changes. The method also includes identifying datasets to rescore through the pipeline. Each of the datasets to rescore have been scored through the pipeline prior to the changes such that previous scores of each of the respective datasets have been determined by the pipeline prior to the changes. The method further includes rerunning, through only the determined impacted components, the datasets, thereby generating rescores of the datasets. The method also includes retrieving each of the previous scores of the datasets, comparing the rescores with the respective previous scores, and transmitting, subject to the comparing, alerts to an output device.

A third party security system having an intelligence unit for receiving and processing vendor related data to generate insights regarding vendor related tasks; a risk assessment unit for receiving and processing risk score data associated with the vendor and for generating a predicted risk score value of the vendor; a legal assessment unit for receiving legal data and for determining based on the legal data whether the vendor is in compliance with a contractual obligation; a vendor tiering unit for receiving the vendor related data and for classifying the vendor into one or more classes based on the vendor related data; a program quality and efficiency analysis unit for receiving the risk score data and for determining an accuracy of the risk score; and a service unit for generating a virtual agent for allowing communication with the system.