# US 2026/0100968 A1 · Systems and methods for autonomous cyber risk remediation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0100968 A1
- Document ID: US20260100968A1
- Status: Published application
- Kind: A1
- Application number: 19/348,969
- Filed: 2025-10-03
- Published: 2026-04-09
- Earliest claimed: 2024-10-03
- Assignees: Rtx Corporation
- Applicants: RTX Corporation
- Inventors: Patrick Duessel; Mark D. Leistner; Justin Robert Scott; Andrew Michael Krycerick; Brett M. Ferrante; Tavis J. Gillard; Troy A. Cottle
- Web page: https://patentgrep.com/patent/US20260100968A1

## CPC

- H04L 63/1433: {Vulnerability analysis}
- H04L 63/1441: {Countermeasures against malicious traffic (countermeasures against attacks on cryptographic mechanisms H04L9/002)}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method includes aggregating network data associated with assets included in the network and associated with an organization, extracting defect features associated with the assets based on control data associated with the network and asset data associated with the assets, extracting threat features related to the organization, an industry associated with the organization, or the assets, determining risk information respectively associated with the assets based on the extracted threat features and the extracted defect features, generating a network graph based on the aggregated network data and the risk information, wherein each node in the network graph represents a respective asset included in the network, performing an automated analysis of the network graph, and generating a task plan based on performing the automated analysis of the network graph. Generating the task plan includes prioritizing individual assets or sets of connected assets in a defined neighborhood of the network.

## Claims

### Claim 1

A method of surgically and effectively remediating risk associated with assets comprised in a network in association with increasing risk reduction impact, comprising:
aggregating network data associated with the assets comprised in the network, wherein the assets are associated with an organization;
extracting defect features associated with the assets based on control data associated with the network and asset data associated with the assets;
extracting threat features related to the organization, an industry associated with the organization, or the assets;
determining risk information respectively associated with the assets based on the extracted threat features and the extracted defect features;
generating a network graph based on the aggregated network data and the risk information, wherein each node in the network graph represents a respective asset comprised in the network;
performing an automated analysis of the network graph; and
generating a task plan based on performing the automated analysis of the network graph, wherein generating the task plan comprises prioritizing individual assets or sets of connected assets in a defined neighborhood of the network.

### Claim 2 (depends on 1)

The method of claim 1, wherein the network data comprises network flow information and device connectivity information among the assets.

### Claim 3 (depends on 1)

The method of claim 1, wherein:
the control data comprises an indication of software vulnerabilities, device configuration defects, and security tool defects associated with the network, and
the asset data comprises an inventory of the assets and incident data associated with the assets.

### Claim 4 (depends on 1)

The method of claim 1, wherein:
determining the risk information comprises mapping the extracted defect features to normalized risk scores using a risk mapping function, and
the risk information comprises the normalized risk scores.

### Claim 5 (depends on 1)

The method of claim 1, wherein the individual assets or the sets of connected assets in the defined neighborhood have a relatively high risk and high importance compared to other assets comprised in the defined neighborhood.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
determining a likelihood of a threat associated with an asset comprised in the network; and
determining a control strength associated with the asset and the threat, wherein the control strength is a measure of an efficacy of a control associated with mitigating the threat,
wherein determining the risk information comprises calculating a risk of exposure for the asset based on:
the likelihood of the threat associated with the asset; and
the control strength associated with the asset and the threat.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
displaying each node in the network graph with a color indicative of a risk of exposure for an asset represented by the node, wherein the method comprises determining the color according to which to display each node, based on a set of candidate risk indicators and a defined threat model; and
displaying directional arrows between nodes in the network graph, wherein:
a directional arrow between two nodes represents an observed direction of data flow between assets represented by the two nodes, and
the directional arrow is displayed with a color and a label according to an amount of the data flow between the two nodes.

### Claim 8 (depends on 1)

The method of claim 1, further comprising identifying, based on performing the automated analysis, a target area of the network graph having a risk density which exceeds a threshold risk density, wherein the task plan comprises one or more actions associated with reducing risk with respect to the target area.

### Claim 9 (depends on 8)

The method of claim 8, wherein:
the target area is a closed k-neighborhood of a node comprised in the network graph; and
the risk density of the target area is based on a concentration of risks associated with other nodes comprised in the target area, wherein the other nodes are directly or indirectly connected to the node within a defined distance which defines the closed k-neighborhood.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
identifying, based on performing the automated analysis, a target node which is included in the network graph and has a risk propagation value which exceeds a threshold risk propagation value, wherein the risk propagation value is a measure of a degree of a risk spreading through the network graph via the target node,
wherein the task plan comprises one or more actions associated with reducing risk with respect to the target node.

### Claim 11 (depends on 1)

The method of claim 1, further comprising identifying, based on performing the automated analysis, a target area of the network graph comprising nodes having respective control deficiencies similar to one another,
wherein the task plan comprises one or more actions associated with reducing risk with respect to the target area.

### Claim 12 (depends on 1)

The method of claim 1, further comprising:
determining, based on performing the automated analysis, one or more actions associated with reducing the risk with respect to the network;
determining a probability of an adverse impact associated with implementing the one or more actions; and
incorporating the one or more actions into the task plan based on the probability.

### Claim 13 (depends on 1)

The method of claim 1, further comprising:
determining an asset importance for each asset comprised among the assets using a crown-centrality measure, wherein the crown-centrality measure is based on a proximity of the asset to a target asset among the assets, wherein the target asset has one or more of a relatively highest value, a relatively highest strategic importance, or a relatively highest performance compared to remaining assets among the assets,
wherein generating the task plan is based on the asset importances determined for the assets.

### Claim 14

A system configured to:
aggregate network data associated with assets comprised in a network, wherein the assets are associated with an organization;
extract defect features associated with the assets based on control data associated with the network and asset data associated with the assets;
extract threat features related to the organization, an industry associated with the organization, or the assets;
determine risk information respectively associated with the assets based on the extracted threat features and the extracted defect features;
generate a network graph based on the aggregated network data and the risk information, wherein each node in the network graph represents a respective asset comprised in the network;
perform an automated analysis of the network graph; and
generate a task plan based on performing the automated analysis of the network graph, wherein in generating the task plan, the system is configured to prioritize individual assets or sets of connected assets in a defined neighborhood of the network.

### Claim 15 (depends on 14)

The system of claim 14, wherein the network data comprises network flow information and device connectivity information among the assets.

### Claim 16 (depends on 14)

The system of claim 14, wherein:
the control data comprises an indication of software vulnerabilities, device configuration defects, and security tool defects associated with the network, and
the asset data comprises an inventory of the assets and incident data associated with the assets.

### Claim 17 (depends on 14)

The system of claim 14, wherein:
determining the risk information comprises mapping the extracted defect features to normalized risk scores using a risk mapping function, and
the risk information comprises the normalized risk scores.

### Claim 18 (depends on 14)

The system of claim 14, wherein the individual assets or the sets of connected assets in the defined neighborhood have a relatively high risk and high importance compared to other assets comprised in the defined neighborhood.

### Claim 19 (depends on 14)

The system of claim 14, further comprising identifying, based on performing the automated analysis, at least one of:
a target area of the network graph having a risk density which exceeds a threshold risk density;
a target node which is included in the network graph and has a risk propagation value which exceeds a threshold risk propagation value, wherein the risk propagation value is a measure of a degree of a risk spreading through the network graph via the target node; or
a second target area of the network graph comprising nodes having respective control deficiencies similar to one another,
wherein the task plan comprises one or more actions associated with reducing risk with respect to the at least one of the target area, the target node, or the second target area.

### Claim 20

An apparatus comprising:
a memory having computer readable instructions and one or more processors for executing the computer readable instructions, wherein the computer readable instructions, when executed by the one or more processors, cause the apparatus to:
aggregate network data associated with assets comprised in a network, wherein the assets are associated with an organization;
extract defect features associated with the assets based on control data associated with the network and asset data associated with the assets;
extract threat features related to the organization, an industry associated with the organization, or the assets;
determine risk information respectively associated with the assets based on the extracted threat features and the extracted defect features;
generate a network graph based on the aggregated network data and the risk information, wherein each node in the network graph represents a respective asset comprised in the network;
perform an automated analysis of the network graph; and
generate a task plan based on performing the automated analysis of the network graph, wherein in generating the task plan, the apparatus is configured to prioritize individual assets or sets of connected assets in a defined neighborhood of the network.
