Abstract: Methods and descriptions are described herein for using user-specific parameters to detect malicious activity in an interaction by a user. In particular, the system may receive user action data representing user actions for users relative to applications. The system may generate, using first user action data representing first user actions of a first user, parameters specific to the first user for determining whether interactions of the first user represent malicious activity. The system may receive, for the first user, a request for a pending interaction with a particular application. The system may then use a first user model trained on the first user action data to identify a set of parameters for identifying the malicious activity. The system may validate the request, in real time, by using the set of parameters to generate a likelihood that the request represents malicious activity.

Abstract: Methods and systems herein identify and redact personally identifiable information. A PII sensitivity detection framework includes multiple layers where each layer corresponds to a computer model. The framework analyzes data stored within different data tables and predicts whether a data column includes PII. The first layer corresponds to an artificial intelligence model that analyzes each column metadata and predicts a first score indicative of a likelihood of PII. The second layer corresponds to a rule-based computer model that uses various rules to determine a second score indicative of a likelihood of PII for each column. The third layer corresponds to a column content model that analyzes content of each column using various natural language processing techniques to generate a third score indicative of a likelihood of PII. The framework masks data being presented to a user based on the scores generated via execution of one or more of the layers.

Abstract: A distributed private ledger function of a server of a first consortium member receives data representing an alias for one of its customers from the customer and also receives data that represents an alias for a customer of a second member replicated by a distributed private ledger function of a server of the second member to all members of the consortium. Thereafter, the distributed private ledger function of the first member's server identifies a recipient account of the second member's customer based on an account pointer associated with the alias of the second member's customer and initiates a transfer of funds from a source account of the first member's customer corresponding to an account pointer associated with the alias for the first member's customer to the identified recipient account of the second member's customer.

Abstract: The systems and methods disclosed herein enable the dynamic selection of one or more AI models to generate an output in response to an input. The system receives, from a computing device, an output generation request including an input for the generation of an output using one or more models from a plurality of models. The system generates expected values for a set of output attributes of the output generation request. For each particular model in the plurality of models, the system determines the capabilities of the particular model, and dynamically select a subset of models from the plurality of models. The system dynamically selects a subset of available system resources to process the input included in the output generation request. The system generates the output by processing the input included in the output generation request using the selected subset of available system resources.

Abstract: A model checking system detects violations and conflicts in security and verification policies by running model checking processes. The system detects privilege escalation attacks in misconfigured identification and access management (“IAM”) policies by modeling security policy documents and IAM actions as logical formulas and then running model checking on the model. The system translates non-Boolean variables, such as string variables, into Boolean variables in order to apply an SAT model checker. The model checker also determines whether a policy violation can be achieved in a finite number of steps by elevating privileges of some compromised principal over multiple iterations of the model checking process, or proves absence thereof.

Abstract: Systems and methods for a software development lifecycle traceability tool. In some aspects, the system may implement a traceability tool that generates a system data stream for an SDLC management platform that stitches together source data from multiple sources, trains a machine learning model to generate progress information and execution risks for a user story on the SDLC management platform, generates a graphical user interface with information for each user story and corresponding progress tracking indicia based on output from the machine learning model, and generates an event-based view of prior actions for each user story and one or more recommended actions to address execution risks.

Abstract: Systems and methods for constructing a layered artificial intelligence (AI) model are provided. The technology determines a set of layers and a set of variables for each layer for the AI model, with each layer relating to a specific domain context of the AI model. Using the layers, the AI model is trained to create layer-specific model logic for each layer using the variables of the layer. By applying the layer-specific model logic to incoming command sets, the model produces detailed layer-specific responses. The trained AI model then generates overall responses to command sets by aggregating the layer-specific responses, along with weights for each layer.

Abstract: Described herein are systems and methods for identifying security vulnerabilities. The systems and methods herein can utilize security vulnerability information to identify potential security threats and can utilize this information to generate an attack using a machine learning model, such as a large language model. Generated attacks can be carried out to assess impact of a security vulnerability. An output can be provided that represents the assessed impact. In some implementations, the systems and methods herein generate patches or other mitigations for security vulnerabilities, which can be tested and deployed to address security vulnerabilities.

Abstract: Systems and methods for novel uses and/or improvements to blockchains and blockchain technology. As one example, systems and methods are described herein for self-validating digital records that may be transferred in real-time through a cross-network registry. For example, in a conventional system, minting a token (e.g., a digital record) involves writing a self-executing program that defines the transfer rules of the digital record. Once the self-executing program is written, it is deployed on a blockchain, and the digital record is minted by publishing it to a blockchain.

Abstract: Systems and methods for novel uses and/or improvements to blockchains and blockchain technology. As one example, systems and methods are described herein for self-validating digital records that may be transferred in real-time through a cross-network registry. For example, in a conventional system, minting a token (e.g., a digital record) involves writing a self-executing program that defines the transfer rules of the digital record. Once the self-executing program is written, it is deployed on a blockchain, and the digital record is minted by publishing it to a blockchain.

Abstract: A network system to allow global usage of data while allowing regional jurisdictions control over sensitive data. Different jurisdictions may declare different types of data as sensitive data that is not to be discoverable by a third party. The system allows the data to be shared across jurisdiction boundaries with complete auditability, traceability, and compliance. The system allows a first jurisdiction computing device to control the usage of the data that is stored outside of the jurisdiction. The technology allows the first jurisdiction to propagate rules, tokenization protocols, and updates to the system to manage the sensitive data. The system detokenizes the data when the data is to be used for an approved purpose by an approved party. If the original jurisdiction has a change in permissions for sensitive data, the jurisdiction can propagate a tokenization to all data stored in the data management system outside of the jurisdiction.

Abstract: Systems and methods are described herein for novel uses and/or improvements for designing user-specific interfaces using machine learning models. When a request to display certain data by an application is received, an application token and a user token may be retrieved and input into a machine learning model to obtain a prediction of a pre-defined user-application interface configuration. A user interface token for the application may then be generated. The user interface token may indicate user interface settings/configuration desired/preferred by a user. The user interface token may then be sent to the application to cause the application to display the data using user interface configurations within the user interface token.

Abstract: The systems and methods provide a model deployment criterion. The model deployment criterion indicates a difference in a value against which the proxy model may be measured to determine when, if ever, the proxy model should be deployed to replace the existing rule engine. The model deployment criterion may be keyed to the proxy model (e.g., based on a difference in its size, throughput speed, number of changes, etc.), the existing rule engine (e.g., based on a difference in its age, update occurrences to its rule base, etc.), and/or comparisons between models (e.g., based on differences in results, throughput speed, efficiency, etc.).

Abstract: Presented herein are systems and methods for the employment of machine learning models for image processing. A method may include a capture of a video feed including image data of a document at a client device. The client device can provide the video feed to another computing device. The method can include, by the client device or the other computing device object recognition for recognizing a type of document and capturing an image exceeding a quality threshold of the document amongst the frames within the video feed. The method may further include the execution of other image processing operations on the image data to improve the quality of the image or features extracted therefrom. The method may further include anti-fraud detection or scoring operations to determine an amount of risk associated with the image data.

Abstract: Systems and methods for uses and/or improvements to artificial intelligence applications. As one example, systems and methods for providing insights into how a given model processes and interprets data as well as the variables, parameters, and/or other determinations that are used to generate results using an observer model. The systems and methods may then compare the insights provided by the observer model to one or more criteria to validate the given model and/or its results against one or more rules, regulations, and/or other requirements, or to retrain the given model.

Abstract: Systems and methods for novel uses and/or improvements to data migration. In particular, systems and methods for data migration of metadata stored in object storage from one container to another, especially in instances when the metadata is destined for ingestion by an artificial intelligence application. The systems and methods ensure that all metadata (e.g., metadata stored in object storage) is preserved during data migration, including metadata such as content type, object lock mode, object lock retain until date, and/or custom metadata.

Abstract: Systems and methods for generating an application profile repository that comprises application profiles. These application profiles may indicate the likely processes executed by a given application as well as the usage metric signatures for those processes. Additionally, the application profiles may indicate the dependencies between applications. To overcome the technical issue of some application profiles being missing or incomplete, the application profile repository may comprise a first set of application profiles corresponding to applications with known dependencies and a second set of application profiles corresponding to applications with virtual dependencies. These virtual dependencies may be determined based on comparisons of the applications, their processes, device usage metrics while the processes are being executed, etc.

Abstract: Systems and methods are for mitigating hindsight bias related to designing and using artificial intelligence models for outlier events. More specifically, systems and methods for the use of synthetic data in the training and/or validation of model predictions in order to prevent overfitting and generate predictions that attempt to predict the unpredictable.

Abstract: Methods and systems are described herein for generating and assigning resources based on timestamps. A plurality of permission messages associated with a plurality of authorization events may be received with each permission message including an authorization timestamp indicating a generation time of a corresponding permission message. In addition, a plurality of data records may be received with each data record including a corresponding plurality of parameters. Based on the permission messages and the data records, a resource multiplier is generated, and resources assigned to each data record are multiplied based on the resource multiplier.