IP Library Granted Patent US 12,563,084
Granted Patent B2
US 12,563,084 · App. 18/628,904 · Granted Feb 24, 2026

Generative AI OPS for cyber security threat detection

Inventors: Abhishek Mehrotra (New Berlin, WI); Steven P. Taylor (Taylor, WI); Jessica L. Wiant (Chagrin Falls, OH); Aparna Ravindranath (Mayfield Heights, OH); Britney Flores (Mayfield Heights, WI)
Assignee: ROCKWELL AUTOMATION TECHNOLOGIES, INC.
H04L63/1433H04L63/1416H04L63/1441
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,563,084
App. No.
18/628,904
Granted
Feb 24, 2026
Kind
B2
Abstract

An industrial security system leverages generative artificial intelligence (AI) to automate the process of identifying software or hardware insecurities on industrial assets, generate recommendations for mitigating these vulnerabilities, and, where appropriate, deploy countermeasures to the vulnerable assets. By leveraging automated asset discovery, real-time asset and network monitoring, and generative AI-assisted vulnerability detection and remediation, the system can reduce the amount of time spent by security administrators in identifying and closing security vulnerabilities within their plant environments, and can alert administrators of potential security issues before those issues become critical.

Claims (51)

1 . A system, comprising:

a memory that stores executable components; and

a processor, operatively coupled to the memory, that executes the executable components, the executable components comprising:

a device interface component configured to collect industrial asset data generated by industrial assets in service within an industrial facility, wherein the industrial asset data comprises identity and configuration information for the industrial assets;

an analysis component configured to

determine, based on analysis of the industrial asset data, whether a subset of the industrial asset data satisfies a condition indicative of a security vulnerability, and

in response to determining that the subset of the industrial data satisfies the condition, formulate, based on the analysis of the industrial data and a model trained with training data, a remedial action predicted to mitigate a risk associated with the security vulnerability, wherein the training data comprises at least technical specifications of the industrial assets; and

a user interface component configured to render, on a client device, information about the security vulnerability and a description of the remedial action,

wherein the analysis component is configured to, in response to determining that the model does not comprise sufficient information to formulate the remedial action, generate a prompt, directed to a generative artificial intelligence (AI) model, designed to obtain a response from the generative AI model that is used by the analysis component to formulate the remedial action.

2 . The system of claim 1 , further comprising a discovery component configured to discover identities and configurations the industrial assets based on analysis of the industrial asset data and to record the identities and configurations as asset information,

wherein the analysis component is configured to perform the analysis based on the asset information.

3 . The system of claim 1 , wherein the training data further comprises at least one of information defining industrial standards; information regarding recommended best practices for industrial design or safety, asset information obtained from vendor knowledgebases, technical specifics or design standards for different types of industrial control applications, knowledge of specific industrial verticals, or control design rules.

4 . The system of claim 3 , wherein the analysis component is configured to generate the prompt to include at least one of a selected subset of the industrial asset data or a selected subset of the training data.

5 . The system of claim 3 , wherein

the user interface is further configured to render a chat interface configured to receive a natural language query directed to security vulnerabilities, including the security vulnerability, detected by the analysis component, and

the analysis component is configured to generate a natural language response to the natural language query based on analysis of the natural language query, a selected subset of the training data, and a response prompted from the generative AI model.

6 . The system of claim 1 , wherein the security vulnerability comprises at least one of an outdated firmware version installed on an industrial asset, of the industrial assets, that leaves the industrial asset vulnerable to unauthorized access; a device configuration setting on the industrial asset that that leaves the industrial asset vulnerable to unauthorized access; or an insecurity in a network architecture design of a plant network on which the industrial assets operate that can allow access to the industrial assets by unauthorized parties.

7 . The system of claim 1 , wherein the remedial action is at least one of installation of new software on an industrial asset of the industrial assets, modification of a device configuration setting on the industrial asset, modification of an asset permission for the industrial asset, modification of a digital certificate on the industrial asset, modification of key-based security for the industrial asset, modification of a network address of industrial asset, an update of the industrial asset's firmware, modification of a firewall parameter for a plant network on which the industrial assets operate, or modification of a whitelist.

8 . The system of claim 7 , further comprising a patch deployment component configured to implement the remedial action in response to a determination by the analysis component that the subset of the industrial asset data satisfies the condition indicative of the security vulnerability.

9 . The system of claim 1 , wherein

the analysis component is further configured to determine a level of risk associated with the security vulnerability, and

the information about the security vulnerability rendered by the user interface component comprises the level of risk.

10 . The system of claim 1 , wherein the information about the security vulnerability rendered by the user interface component comprises at least one of a description of the security vulnerability, an identity of an industrial asset affected by the security vulnerability, a description of a manufacturing risk posed by the vulnerability, a description of a safety risk posed by the security vulnerability, or a predicted cost associated with the security vulnerability.

11 . A method, comprising:

collecting, by a system comprising a processor, industrial asset data from industrial assets operating within an industrial plant, wherein the industrial asset data comprises identity and configuration information for the industrial assets;

determining, by the system based on analysis of the industrial asset data, whether a subset of the industrial asset data satisfies a condition indicative of a security vulnerability;

in response to determining that the subset of the industrial data satisfies the condition, determining, by the system, based on the analysis of the industrial data and a model trained with training data, a remedial action predicted to mitigate a risk associated with the security vulnerability, wherein the training data comprises at least technical specifications of the industrial assets; and

rendering, by the system on a client device, information about the security vulnerability and a description of the remedial action,

wherein the determining of the remedial action comprises, in response to determining that the model does not comprise sufficient information to determine the remedial action, generating a prompt, directed to a generative artificial intelligence (AI) model, designed to obtain a response from the generative AI model that is used by the system to determine the remedial action.

12 . The method of claim 11 , further comprising:

discovering, by the system, identities and configurations the industrial assets based on analysis of the industrial asset data; and

recording, by the system, the identities and configurations as asset information,

wherein the determining of whether the subset of the industrial asset data satisfies the condition comprises performing the analysis on the industrial asset data and the asset information.

13 . The method of claim 11 , wherein the training data further comprises at least one of information defining industrial standards, information regarding recommended best practices for industrial design or safety, asset information obtained from vendor knowledgebases, technical specifics or design standards for different types of industrial control applications, knowledge of specific industrial verticals, or control design rules.

14 . The method of claim 13 , wherein the generating of the prompt comprises generating the prompt to include at least one of a selected subset of the industrial asset data or a selected subset of the training data.

15 . The method of claim 11 , further comprising:

receiving, by the system via a chat interface, a natural language query regarding security vulnerabilities, including the security vulnerability, detected by the system, and

in response to the receiving of the natural language query, generating, by the system, a natural language response to the natural language query based on analysis of the natural language query, a selected subset of the training data, and a response prompted from the generative AI model.

16 . The method of claim 11 , wherein the security vulnerability comprises at least one of an outdated firmware version installed on an industrial asset, of the industrial assets, that leaves the industrial asset vulnerable to unauthorized access; a device configuration setting on the industrial asset that that leaves the industrial asset vulnerable to unauthorized access; or an insecurity in a network architecture design of a plant network on which the industrial assets operate that can allow access to the industrial assets by unauthorized parties.

17 . The method of claim 11 , wherein the remedial action is at least one of installation of new software on an industrial asset of the industrial assets, modification of a device configuration setting on the industrial asset, modification of an asset permission for the industrial asset, modification of a digital certificate on the industrial asset, modification of key-based security for the industrial asset, modification of a network address of industrial asset, an update of the industrial asset's firmware, modification of a firewall parameter for a plant network on which the industrial assets operate, or modification of a whitelist.

18 . The method of claim 17 , further comprising implementing, by the system, the remedial action in response to determining that the subset of the industrial data satisfies the condition.

19 . A non-transitory computer-readable medium having stored thereon instructions that, in response to execution, cause a system comprising a processor to perform operations, the operations comprising:

collecting industrial asset data from industrial assets operating within an industrial plant, wherein the industrial asset data comprises identity and configuration information for the industrial assets;

determining, based on analysis of the industrial asset data, whether a subset of the industrial asset data satisfies a condition indicative of a security vulnerability;

in response to determining that the subset of the industrial data satisfies the condition, formulating, based on the analysis of the industrial data and a model trained with training data, a remedial action predicted to mitigate a risk associated with the security vulnerability, wherein the training data comprises at least technical specifications of the industrial assets; and

rendering, on a client device, information about the security vulnerability and a description of the remedial action,

wherein the formulating of comprises, in response to determining that the model does not comprise sufficient information to formulate the remedial action, generating a prompt, directed to a generative artificial intelligence (AI) model, designed to obtain a response from the generative AI model that is used by the system to formulate the remedial action.

20 . The non-transitory computer-readable medium of claim 19 , further comprising:

discovering identities and configurations the industrial assets based on analysis of the industrial asset data; and

recording the identities and configurations as asset information,

wherein the determining of whether the subset of the industrial asset data satisfies the condition comprises performing the analysis on the industrial asset data and the asset information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 8, 2024
From: MEHROTRA, ABHISHEK; TAYLOR, STEVEN P.; WIANT, JESSICA L.; RAVINDRANATH, APARNA; FLORES, BRITNEY
To: ROCKWELL AUTOMATION TECHNOLOGIES, INC.
Reel/Frame 067030/0331 →
Continuity (1)
Related Publication 20250317464A1 · Oct 9, 2025
References Cited (10)
US 11790081B2 · D'Amato · 2023 [cited by examiner]
US 12137111B2 · Bassi · 2024 [cited by examiner]
US 20160248800A1 · Ng · 2016 [cited by examiner]
US 20160330222A1 · Brandt · 2016 [cited by examiner]
US 20170310690A1 · Mestha · 2017 [cited by examiner]
US 20180316701A1 · Holzhauer · 2018 [cited by examiner]
US 20190056722A1 · Abbaszadeh · 2019 [cited by examiner]
US 20200137090A1 · Holzhauer · 2020 [cited by examiner]
US 20230058974A1 · Yan · 2023 [cited by examiner]
US 20240163304A1 · Gupta · 2024 [cited by examiner]