# US 2025/0094572 A1 · Generation of simplified security software interaction and summaries using generative ai

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

- Number: US 2025/0094572 A1
- Document ID: US20250094572A1
- Status: Published application
- Kind: A1
- Application number: 18/468,197
- Filed: 2023-09-15
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Acronis International GmbH
- Applicants: Acronis International GmbH
- Inventors: Candid Wuest; Serg Bell; Stanislav Protasov
- Web page: https://patentgrep.com/patent/US20250094572A1

## CPC

- G06F 21/554: {involving event detection and direct action}
- G06N 3/08: Learning methods
- G06F 2221/034: Test or assess a computer or a system
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems and methods for mitigating potential security incidents. A system includes a data ingestion module, a graphical user interface (GUI), a generative AI model, an enrichment module, and a mitigation module. The generative AI model is pretrained on a large language model (LLM) using a dataset of known security incidents and the computer system's infrastructure, and analyses potential security incidents and generates incident overviews, leveraging its understanding of attack frameworks and previous incident data. The enrichment module incorporates user interactions, enhancing the incident overviews with accurate information. The mitigation module proposes mitigation actions based on the generative AI model's insights gained from prior incidents. The system enables natural language interaction through the GUI and provides graphical representations of the incidents. With its ability to summarize incidents, propose actions, and support user understanding, the system offers an efficient approach to mitigating security incidents.

## Claims

### Claim 1

A computer-implemented method of mitigating a potential security incident in a computer system, the method comprising:
pretraining a generative AI model based on a large language model (LLM) using a training dataset of known security incidents and an infrastructure of the computer system, the generative AI model further trained in conversational interactions with a user;
receiving data associated with a potential security incident;
analyzing the potential security incident using the generative AI model to generate a security incident overview;
presenting the security incident overview to a user using a graphical user interface;
receiving at least one question from the user through the graphical user interface;
answering the at least one question using the generative AI model;
enriching the security incident overview based on the answer, including presenting the answer to the user using the graphical user interface; and
proposing a mitigation action for the potential security incident.

### Claim 2 (depends on 1)

The method of claim 1, wherein the generative AI model is pretrained on question-answer pairs based on at least one of a cybersecurity framework or an attack framework.

### Claim 3 (depends on 1)

The method of claim 1, wherein the generative AI model is pretrained on data from previous security incidents to determine a taxonomy of attacks and an association between attack techniques.

### Claim 4 (depends on 1)

The method of claim 1, further comprising calibrating the generative AI model based on an infrastructure topology of the computer system, and wherein the calibration is repeated at an interval or when the infrastructure has changed.

### Claim 5 (depends on 1)

The method of claim 1, wherein the data associated with the potential security incident is received from at least one of an EDR (Endpoint Detection and Response) solution, an XDR (Extended Detection and Response) solution, a SIEM (Security Information and Event Management) solution, or a log file.

### Claim 6 (depends on 1)

The method of claim 1, further comprising triggering data collection, including generating a forensic memory dump of an involved computer, for analysis by the generative AI model.

### Claim 7 (depends on 1)

The method of claim 1, wherein the user interacts with the generative AI model using a natural language query.

### Claim 8 (depends on 1)

The method of claim 1, wherein the generative AI model proposes the mitigation action based on previous incidents learned during the training of the large language model.

### Claim 9

A computer system for mitigating potential security incidents, the system comprising:
a hardware processor implemented on a computing device; and
instructions that, when executed by the hardware processor, cause the hardware processor to implement:
a data ingestion module configured to receive data associated with at least one potential security incident,
a graphical user interface configured to present the security incident overview to a user and receive at least one question from the user,
a generative AI model pretrained based on a large language model (LLM) using a training dataset of known security incidents and an infrastructure of the computer system, the generative AI model further trained in conversational interactions with a user, and configured to:
analyze the potential security incident using the generative AI model to generate a security incident overview, and
answer the at least one question,
an enrichment module configured to enrich the security incident overview based on the answer, including presenting the answer to the user using the graphical user interface, and
a mitigation module configured to propose a mitigation action for the potential security incident.

### Claim 10 (depends on 9)

The computer system of claim 9, further comprising a calibration module configured to calibrate the generative AI model based on an infrastructure topology of the computer system.

### Claim 11 (depends on 9)

The computer system of claim 9, wherein the data ingestion module is configured to receive the data associated with the at least one potential security incident from one or more security solutions, a SIEM (Security Information and Event Management) solution, a log file, or a sensor.

### Claim 12 (depends on 9)

The computer system of claim 9, wherein the mitigation module is further configured to propose the mitigation action for the potential security incident based on previous incidents learned during the training of the large language model.

### Claim 13 (depends on 9)

The computer system of claim 9, wherein the generative AI model is further configured to generate a graphical overview of the computer system and data flows related to the security incident.

### Claim 14 (depends on 9)

The computer system of claim 9, wherein the generative AI model is further configured to map IP addresses and system names to meaningful names based on a corporate environment.

### Claim 15 (depends on 1)

The method of claim 1, wherein the generative AI model is further configured to generate a summary of the security incident in plain natural language.

### Claim 16 (depends on 9)

The computer system of claim 9, wherein the generative AI model is pretrained on question-answer pairs based on at least one of a cybersecurity framework or an attack framework.

### Claim 17 (depends on 9)

The computer system of claim 9, wherein the generative AI model is pretrained on data from previous security incidents to determine a taxonomy of attacks and an association between attack techniques.

### Claim 18 (depends on 9)

The computer system of claim 9, wherein the data associated with the potential security incident is received from at least one of an EDR (Endpoint Detection and Response) solution, an XDR (Extended Detection and Response) solution, a SIEM (Security Information and Event Management) solution, or a log file.

### Claim 19 (depends on 10)

The computer system of claim 10, wherein the calibration is repeated at an interval or when the infrastructure has changed.

### Claim 20

A computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform a method of mitigating potential security incidents in a computer system, the method comprising:
pretraining a generative AI model based on a large language model (LLM) using a training dataset of known security incidents and an infrastructure of the computer system, the generative AI model further trained in conversational interactions with a user;
receiving data associated with a potential security incident;
analyzing the potential security incident using the generative AI model to generate a security incident overview;
presenting the security incident overview to a user using a graphical user interface;
receiving at least one question from the user via the graphical user interface; answering the at least one question using the generative AI model;
enriching the security incident overview based on the answer, including presenting the answer to the user using the graphical user interface; and
proposing a mitigation action for the potential security incident.
