# US 2024/0406190 A1 · Threat prediction in a streaming system

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

- Number: US 2024/0406190 A1
- Document ID: US20240406190A1
- Status: Published application
- Kind: A1
- Application number: 18/203,603
- Filed: 2023-05-30
- Published: 2024-12-05
- Earliest claimed: 2023-05-30
- Assignees: CrowdStrike, Inc.
- Applicants: CrowdStrike, Inc.
- Inventors: Theo Chihaia; Jaclyn Abrams; Joel Robert Spurlock; Joseph Faulhaber
- Web page: https://patentgrep.com/patent/US20240406190A1

## CPC

- H04L 63/1416: {Event detection, e.g. attack signature detection}
- H04L 41/16: using machine learning or artificial intelligence
- H04L 63/1433: {Vulnerability analysis}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Techniques for aggregating data usable for generating security recommendations are discussed herein. A system can aggregate detection data from host devices associated with different organizations based on profile information describing each organization. The system can analyze the aggregated data to identify potential security threats in a data stream, and generate recommendation data usable for defending the data stream from future malicious events.

## Claims

### Claim 1

A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
receiving detection data comprising a) first malicious event information in a first data stream associated with a first computing device of a first organization, b) second malicious event information in a second data stream associated with a second computing device of a second organization, c) technique information identifying one or more techniques associated with a malicious event in the first data stream or the second data stream, and d) actor information identifying a source of the first malicious event information or the second malicious event information;
receiving profile data comprising a first profile of the first organization, the first profile comprising one or more of: a location of the first computing device, a size of the first organization, an organization type, data infrastructure information, or subsidiary information;
inputting the detection data and the profile data into a model;
determining, based on the model, a visualization indicating one or more of: vulnerabilities exposed during the malicious event, an actor that initiated the malicious event, or malware executed in association with the malicious event; and
configuring recommendation data for the first computing device, the recommendation data including the visualization and information indicating a portion of the first data stream to protect from a future malicious event.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the detection data further comprises a first graph to represent the first malicious event information and a second graph to represent the second malicious event information;
the malicious event identifies a malicious process or thread in the first data stream or the second data stream; and
the visualization represents a graph, a map, an image, a diagram, or an animation.

### Claim 3 (depends on 1)

The system of claim 1, wherein the model is a first model, and the operations further comprising:
outputting the visualization to a second model or a human; and
receiving input from the second model or the human to modify the visualization as a modified visualization,
wherein the recommendation data comprises the modified visualization.

### Claim 4 (depends on 1)

The system of claim 1, the operations further comprising:
receiving a message from the first computing device requesting recommendation data for protecting the first data stream from the future malicious event; and
accessing, based at least in part on receiving the message, the first profile associated with the first computing device from a database,
wherein configuring the recommendation data is based at least in part on accessing the first profile.

### Claim 5 (depends on 1)

The system of claim 1, the operations further comprising:
determining metadata describing the visualization, the metadata comprising one or more of: a location of the malicious event, an average size of the first organization and the second organization, the organization type, a human-readable name of the visualization, a creation time of the visualization, one or more profiles used to generate the visualization:
associating the metadata and the visualization as a visualization profile; and
storing the visualization profile in a database.

### Claim 6 (depends on 5)

The system of claim 5, the operations further comprising:
receiving a message from a third computing device requesting security information to protect a third data stream from a potential malicious event:
identifying a third profile associated with the third computing device:
comparing, based at least in part on receiving the message, the metadata of the visualization profile with information of the third profile; and
transmitting the recommendation data to the third computing device based at least in part on the comparing.

### Claim 7

One or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:
receiving first data comprising a) first malicious event information in a first data stream associated with a first computing device of a first organization, b) second malicious event information in a second data stream associated with a second computing device of a second organization, and c) technique information identifying one or more techniques associated with a malicious event in the first data stream or the second data stream;
receiving second data representing a first profile of the first organization, the first profile comprising one or more of: a location of the first computing device, a size of the first organization, an organization type, data infrastructure information, or subsidiary information;
inputting the first data and the second data into a model;
determining, by the model, output data including a visualization indicating one or more of: vulnerabilities exposed during the malicious event, an actor that initiated the malicious event, or malware executed in association with the malicious event; and
configuring third data for the first computing device, the third data including the visualization and information indicating a portion of the first data stream to protect from a future malicious event.

### Claim 8 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, the operations further comprising:
determining that the first organization is associated with a security recommendation service,
wherein configuring the third data is based at least in part on the first organization being associated with the security recommendation service.

### Claim 9 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, wherein:
the first data further comprises actor information identifying a source of the first malicious event information or the second malicious event information.

### Claim 10 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, wherein:
the first data further comprises a first graph to represent the first malicious event information and a second graph to represent the second malicious event information;
the malicious event identifies a malicious process or thread in the first data stream or the second data stream; and
the visualization represents a graph, a map, an image, a diagram, or an animation.

### Claim 11 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, wherein the model is a first model, and the operations further comprising:
outputting the visualization to a second model or a human; and
receiving input from the second model or the human to modify the visualization as a modified visualization,
wherein the third data comprises the modified visualization.

### Claim 12 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, the operations further comprising:
receiving a message from the first computing device requesting recommendation data for protecting the first data stream from the future malicious event; and
accessing, based at least in part on receiving the message, the first profile associated with the first computing device from a database,
wherein configuring the third data is based at least in part on accessing the first profile.

### Claim 13 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, the operations further comprising:
determining metadata describing the visualization, the metadata comprising one or more of: a location of the malicious event, an average size of the first organization and the second organization, the organization type, a human-readable name of the visualization, a creation time of the visualization, one or more profiles used to generate the visualization;
associating the metadata and the visualization as a visualization profile; and
storing the visualization profile in a database.

### Claim 14 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, wherein:
the information in the third data identifies previous malicious behavior initiated by the actor to enable a human associated with the first computing device to understand a reason for the future malicious event.

### Claim 15 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, wherein the third data represents recommendation data, and the operations further comprising:
receiving a set of profiles representing different organizations;
comparing first information associated with the recommendation data with respective information associated with each profile in the set of profiles; and
transmitting the recommendation data to a third computing device to protect a third data stream from the future malicious event.

### Claim 16 (depends on 7)

The one or more non-transitory computer-readable media of claim 7, the operations further comprising:
determining a similarity score between the first profile and a second profile associated with the second organization;
comparing the similarity score to a threshold value; and
determining the output data comprising the visualization based at least in part on the similarity score being equal or above the threshold value.

### Claim 17

A computer-implemented method comprising:
receiving first data comprising a) first malicious event information in a first data stream associated with a first computing device of a first organization, b) second malicious event information in a second data stream associated with a second computing device of a second organization, and c) technique information identifying one or more techniques associated with a malicious event in the first data stream or the second data stream;
receiving second data representing a first profile of the first, the first profile comprising one or more of: a location of the first computing device, a size of the first organization, an organization type, data infrastructure information, or subsidiary information;
inputting the first data and the second data into a model;
determining, based on the model, output data indicating one or more of: vulnerabilities exposed during the malicious event, an actor that initiated the malicious event, or malware executed in association with the malicious event; and
configuring third data for the first computing device, the third data including the output data and information indicating a portion of the first data stream to protect from a future malicious event.

### Claim 18 (depends on 17)

The computer-implemented method of claim 17, wherein:
the first data further comprises a first graph to represent the first malicious event information and a second graph to represent the second malicious event information;
the malicious event identifies a malicious process or thread in the first data stream or the second data stream; and
the output data represents a graph, a map, an image, a diagram, or an animation.

### Claim 19 (depends on 17)

The computer-implemented method of claim 17, further comprising:
receiving a message from the first computing device requesting recommendation data for protecting the first data stream from the future malicious event; and
accessing, based at least in part on receiving the message, the first profile associated with the first computing device from a database,
wherein configuring the recommendation data is based at least in part on accessing the first profile.

### Claim 20 (depends on 17)

The computer-implemented method of claim 17, wherein the output data comprises a visualization, and further comprising:
determining metadata describing the visualization, the metadata comprising one or more of: a location of the malicious event, an average size of the first organization and the second organization, the organization type, a human-readable name of the visualization, a creation time of the visualization, one or more profiles used to generate the visualization;
associating the metadata and the visualization as a visualization profile; and
storing the visualization profile in a database.
