Citibank, N.a.

Pramod Goyal

Prithvi Narayana Rao

Miriam Silver

William Franklin Cameron

Manjit Rajaretnam

James Myers

Daniel Lewandowski

Philip Davies

Biraj Krushna Rath

Ramkumar Ayyadurai

Payal Jain

Stuart Murray

Mariusz Saternus

Tariq Husayn Maonah

Chamindra Desilva

Vishal Mysore

Shardul Malviya

Samantha Cory

Deepak Jain

Wayne Liao

Sofia Rahman

Prashant Praveen

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

Systems and methods for determining and displaying comparative platform-specific security vulnerabilities with respect to cloud-based computing platforms are disclosed. To compare platform-specific security vulnerabilities of cloud-based computing platforms, the system detects a user interaction at a webpage for a network operation. The system then determines a first set of computing aspects associated with a set of cloud-based computing platforms using response data received from a processing of the network operation. The system then identifies a second set of computing aspects associated with a comparative cloud-based computing system platform and determines an overall-computing aspect impact level for associated computing aspects of the second set of computing aspects. The system then generates for display at a graphical user interface (GUI), a graphical layout indicating a graphical representation of each determined overall-computing aspect impact level for the respective cloud-based computing system platforms.

Comparative real-time end-to-end security vulnerabilities determination and visualization

Systems and methods for providing user-induced variable identification of end-to-end computing system security impact information via a user interface are disclosed. The system receives at a graphical user interface (GUI), a user calibration of a graphical security vulnerability element. The system then determines a set of computing system components that interact with data associated with the network operation based on a transmission of the network operation associated with a computing system. The system then determines a set of security vulnerabilities associated with each computing system component of the set of computing system components using a third-party resource. The system then applies a decision engine on the set of security vulnerabilities to determine a set of impacted computing-aspects associated with the set of computing system components. The system then generates for display a graphical representation of the set of impacted computing-aspects satisfying the security condition of the user calibration.

Providing user-induced variable identification of end-to-end computing system security impact information systems and methods

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

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 determining and displaying platform-specific end-to-end security vulnerabilities via a graphical user interface (GUI) are disclosed. To provide users with visual indications of vulnerable computing aspects associated with a computing platform, the system identifies computing aspects associated with a platform. The system then obtains from a security entity, security-vulnerability descriptions that are associated with the platform. Using the security-vulnerability descriptions, the system then determines threat levels for each security-vulnerability description and then, using the determined threat levels, determines a computing aspect impact level for each computing aspect associated with the platform. The system then generates for display on a GUI, a graphical layout comprising each computing aspect impact level for each computing aspect associated with the platform.

Growing community of inventors

Ahmedabad, India

Pramod Goyal