Generative AI and agentic AI systems and methods for prevention, detection, mitigation and remediation of cybersecurity threats
OwnerBrian McCarsoninventor
Life of this patent
Estimating the term…
Abstract
Generative AI systems and methods are developed to provide recommendations regarding the prevention, detection, mitigation, and/or remediation of cybersecurity threats as determined from a range of available data sources. A consistent, semantic metadata structure is described as well as a hypothesis generating and testing system capable of generating predictive analytics models in a non-supervised or partially supervised mode. Users and/or AI agents (i.e., a form of “agentic AI”) may then subscribe to the data for the use in cybersecurity analytics, protection, mitigation, containment, remediation, and/or counterattacks of cybersecurity threats.
Claims18
A generative artificial intelligence (AI) system for cybersecurity applications, comprising:
- a plurality of data sources, wherein at least one of the data sources is sensor data derived from direct observation of activity within an environment;
- a context-aware AI database;
- a probationary database;
- an analytics engine communicatively coupled to the plurality of data sources, the context-aware AI database, and the probationary database;
- wherein the analytics engine is configured to:
- (a) generate a hypothesis object comprising independent variables, a dependent variable including a leading indicator of cybersecurity attack activity, a machine learning model trained from available data, and metadata associated therewith based on the data sources, wherein the leading indicator includes a recommendation or action related to at least one of:
- prevention of a cyberattack, detection of a cyberattack, mitigation of a cyberattack, and remediation of a cyberattack;
- (b) train the machine learning model associated with the hypothesis object to produce experimental results;
- (c) store the hypothesis object and the experimental results in the context-aware AI database in response to determining that the performance metric of the machine learning model meets a predetermined performance criterion;
- (d) store the hypothesis object and the experimental results in the probationary database in response to determining that the performance metric of the machine learning model does not meet a predetermined performance criterion;
- and a publishing module configured to provide, to one or more subscribers, the leading indicator associated with at least one of the corporate entity and a product associated with the corporate entity, as computed by the trained machine learning model stored within the context-aware AI database while processing contemporaneous information received from the data sources.
Dependencies are inferred from the claim text.