Citibank, N.a.

William Franklin Cameron

Miriam Silver

Manjit Rajaretnam

Prithvi Narayana Rao

Pramod Goyal

James Myers

Daniel Lewandowski

Philip Davies

Biraj Krushna Rath

Payal Jain

Stuart Murray

Ramkumar Ayyadurai

Mariusz Saternus

Tariq Husayn Maonah

Robin Jose Kurian

Chamindra Desilva

Vishal Mysore

Shardul Malviya

Samantha Cory

Deepak Jain

Wayne Liao

Jason Ryan Engelbrecht

John E Ortega, Jr

Alberto Cetoli

Sofia Rahman

Ganesh Prasad Bhat

Prashant Praveen

Wei Jie Ng

Subramanian Sankaran

Ramee S Karthikeyan

Ines Teixeira

Yael Man

Minjeong Cho

Laura Mcneil

Ryan Bergeron

Matthew Ryan Mitsui

Cameron Paul Lim

Alex Michael Eng

Joseph Julius Bosco Arockia Dass

Brenda Dykgraaf

Systems and methods are disclosed comprising instructions to receive a request to evaluate authorization of a development service that comprises a digital artifact set, each digital artifact in the digital artifact set, access an authorization schema set available for the development service, identify an applicable authorization schema from the authorization schema set via comparing the content embeddings of the digital artifacts and the reference embeddings of the authorization schemas, retrieve a historical artifact attribute set representing tracked development actions for prior development services authorized via the applicable authorization schema, predict an authorization status for the development service using the historical artifact attribute set and the artifact attribute set, configure for display a visual representation of the applicable authorization schema and the mapped at least one digital artifact of the development service.

Robust artifacts mapping and authorization systems and methods for operating the same

Systems and methods for constructing layered prompts to operate as input into a pre-trained large language model (LLM). The method involves obtaining a set of application domains in which the LLM will be used. Using these application domains, a set of guidelines is determined, defining operation boundaries for the LLM. A set of layers is determined, each associated with the guidelines and including variables representing attributes identified within those guidelines. Using these layers, a first layered prompt is constructed to test the initial operation boundaries of the guidelines and is supplied to the LLM to generate a set of responses. Based on the responses, a second layered prompt is dynamically constructed to test additional operation boundaries, ensuring iterative refinement and contextual relevance.

Layered multi-prompt engineering for pre-trained large language models

Systems and methods are described that allow for updating of software applications during testing of the application to detect errors as a result of execution of portions of the software application that prevent downstream portions of the software application from being evaluated. In an example, systems are described that are configured to detect errors during application execution. When an error is detected, the system obtains and executes specific script sets to debug the application. Based on the results of these debug operations, the system generates error reports that indicate issues within the software workflow. This ensures that errors in one part of the software do not hinder the evaluation of subsequent parts, allowing for a more efficient and thorough testing process.

Systems and methods for integrating script development and script validation platforms based on detected dependency branches in script code

Described herein are systems and methods for discovering and proactively mitigating previously unknown security vulnerabilities. The systems and methods herein can utilize security vulnerability information to discover 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.

Generative cybersecurity exploit discovery and evaluation

The systems and methods disclosed herein receives artifacts generated using a first set of models within a multi-model superstructure. The multi-model superstructure includes a second set of models to test the first set of models. The multi-model superstructure dynamically routes the artifacts of the first set of models to one or more models of the second set of models by (i) determining a set of dimensions of the artifacts against which to evaluate the artifacts and (ii) identifying the models in the second set used to test the particular dimension. The second set of models then assesses each artifact against a set of assessment metrics. If an artifact fails to meet one or more assessment metrics, the second set of models generates actions to align the artifact with the set of assessment metrics.

Dynamic multi-model monitoring and validation for artificial intelligence models

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.

System and method for constructing a layered artificial intelligence model

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.

Generative cybersecurity exploit synthesis and mitigation

Described herein are systems and methods for verifying the integrity of data, such as data used for training machine learning models. Some implementations are directed to verifying the provenance of datasets, the contents of datasets, or both. In some implementations, multiple filters are selected for verifying the contents of datasets. Filters can be selected based on rules, random selection, or using a machine learning model in some implementations. In some implementations, data cleaning is provided.

Detection and mitigation of machine learning model adversarial attacks

Systems and methods for measuring, grading, evaluating, and comparing AI models via a graphical user interface are disclosed. The technology obtains a set of application domains of the AI model in which an AI model will be used. The application domains are mapped to one or more guidelines to determine a set of guidelines that define operational boundaries of the AI model. The guidelines are used to generate assessment domains, each associated with specific benchmarks that include indicators of a degree of satisfaction with the guidelines. For each assessment domain, assessments are constructed to evaluate the AI model's degree of satisfaction with the corresponding guidelines. The AI model is then evaluated against the assessments. Based on these comparisons, grades are assigned to the AI model for each assessment domain. The application-domain-specific grades are generated and displayed at a GUI, reflecting the AI model's degree of satisfaction with the guidelines.

End-to-end measurement, grading and evaluation of pretrained artificial intelligence models via a graphical user interface (GUI) systems and methods

Systems and methods for evaluating a pre-trained artificial intelligence (AI) model using layered prompts. The system obtains a set of application domains in which the AI model will be used, and a set of guidelines that define one or more operational boundaries of the AI model. The system determines a set of layers, where each layer is associated with corresponding guidelines and mapped to a set of variables and benchmarks. Each variable represents an attribute within the guidelines and each benchmark indicates the degree of satisfaction of the AI model with the guidelines. The AI model is dynamically evaluated against these benchmarks using a series of assessments. Subsequent assessments are dynamically constructed based on the outcomes of previous assessments. Scores are assigned to the AI model for each layer by comparing the expected and actual responses. The results are then displayed in a graphical user interface (GUI).

Layered measurement, grading and evaluation of pretrained artificial intelligence models

Abdominal exercise device

Growing community of inventors

Jacksonville, FL, United States of America

William Franklin Cameron