Generative artificial intelligence for a network security scanner

Patent metadata

Field	Value
Publication number	US-12461841-B2
Application number	US-202318215992-A
Country	US
Kind code	B2
Filing date	Jun 29, 2023
Priority date	Apr 3, 2023
Publication date	Nov 4, 2025
Grant date	Nov 4, 2025

Abstract

A computer system for network security vulnerability inspection may include one or more processors configured to: transmit a prompt for network security vulnerability testing code to an ML chatbot (or voice bot) to cause an ML model to generate the network security vulnerability testing code, receive the network security vulnerability testing code from the ML chatbot (or voice bot), scan a network to identify network computing devices, scan one or more of the network computing devices to identify security vulnerabilities and vulnerable network computing devices, and/or communicate the security vulnerabilities and/or vulnerable network computing devices to a user.

First claim

What is claimed:

1 . A computer system for network security vulnerability inspection, the computer system comprising:
one or more processors; a memory storing executable instructions thereon that, when executed by the one or more processors, cause the one or more processors to:
transmit a prompt for a network security vulnerability testing code to a machine learning (ML) chatbot to cause an ML model to generate the network security vulnerability testing code, and
receive the network security vulnerability testing code from the ML chatbot,
wherein the network security vulnerability testing code comprises further instructions that, when executed by the one or more processors, cause the one or more processors to:
scan a network to identify network computing devices,
scan one or more of the network computing devices to identify security vulnerabilities and vulnerable network computing devices, and
communicate an identification of the security vulnerabilities and/or the vulnerable network computing devices to a user
wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
receive a security vulnerability announcement,
transmit a prompt for updated network security vulnerability testing code and the security vulnerability announcement to the ML chatbot to cause the ML model to generate the updated network security vulnerability testing code,
receive the updated network security vulnerability testing code from the ML chatbot, and
alert the user regarding the security vulnerability announcement and/or the updated network security vulnerability testing code.

2 . The computer system of claim 1 , wherein scanning one or more of the network computing devices comprises testing the network computing devices with denial of service, SQL injection, LDAP injection, buffer overflow, stack overflow, or cross-site scripting exploits.

3 . The computer system of claim 1 , wherein the network security vulnerability testing code comprises further instructions that, when executed by the one or more processors, cause the one or more processors to:
identify recommendations for resolving the security vulnerabilities, and communicate the recommendations to the user.

4 . The computer system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
transmit the identification of the vulnerable computing devices to a network firewall, and cause the network firewall to update a firewall security policy.

5 . The computer system of claim 1 , wherein the security vulnerability announcement is in text format and/or common vulnerabilities and exposures format.

6 . The computer system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
receive the security vulnerability announcement from one or more of:
(i) email message(s),
(ii) social media account(s), or
(iii) website(s).

7 . The computer system of claim 1 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
train the ML model with a training dataset, and validate the ML model with a validation dataset, wherein the training dataset and the validation dataset comprise a set of security vulnerability announcements and a set of network security vulnerability testing code.

8 . A computer-implemented method for network security vulnerability inspection, the method comprising:
transmitting a prompt for a network security vulnerability testing code to a machine learning (ML) chatbot to cause an ML model to generate the network security vulnerability testing code; receiving the network security vulnerability testing code from the ML chatbot; and executing the network security vulnerability testing code to:
scan a network to identify network computing devices,
scan one or more of the network computing devices to identify security vulnerabilities and vulnerable network computing devices, and
communicate an identification of the security vulnerabilities and/or the vulnerable network computing devices to a user;
wherein the method further comprises:
receiving a security vulnerability announcement;
transmitting a prompt for updated network security vulnerability testing code and the security vulnerability announcement to the ML chatbot to cause the ML model to generate the updated network security vulnerability testing code;
receiving the updated network security vulnerability testing code from the ML chatbot; and
alerting the user regarding the security vulnerability announcement and/or the updated network security vulnerability testing code.

9 . The computer-implemented method of claim 8 , wherein scanning the one or more network computing devices comprises testing the network computing devices with denial of service, SQL injection, LDAP injection, buffer overflow, stack overflow, or cross-site scripting exploits.

10 . The computer-implemented method of claim 8 further comprising executing the network security vulnerability testing code to:
identify recommendations for resolving the security vulnerabilities; and
communicate the recommendations to the user.

11 . The computer-implemented method of claim 8 further comprising executing the network security vulnerability testing code to:
transmit the identification of the vulnerable computing devices to a network firewall; and
cause the network firewall to update a firewall security policy.

12 . The computer-implemented method of claim 8 further comprising:
training the ML model with a training dataset, and
validating the ML model with a validation dataset,
wherein the training dataset and the validation dataset comprise a set of security vulnerability announcements and a set of network security vulnerability testing code.

13 . A non-transitory computer readable storage medium storing computer readable instructions for network security vulnerability inspection, wherein the instructions when executed on one or more processors cause the one or more processors to:
transmit a prompt for a network security vulnerability testing code to a machine learning (ML) chatbot to cause an ML model to generate the network security vulnerability testing code, and receive the network security vulnerability testing code from the ML chatbot, wherein the network security vulnerability testing code comprises further instructions that, when executed by the one or more processors, cause the one or more processors to:
scan a network to identify network computing devices,
scan one or more of the network computing devices to identify security vulnerabilities and vulnerable network computing devices, and
communicate an identification of the security vulnerabilities and/or vulnerable network computing devices to a user;
wherein the instructions, when executed by the one or more processors, further cause the one or more processors to:
receive a security vulnerability announcement,
transmit a prompt for updated network security vulnerability testing code and the security vulnerability announcement to the ML chatbot to cause the ML model to generate the updated network security vulnerability testing code,
receive the updated network security vulnerability testing code from the ML chatbot, and
alert the user regarding the security vulnerability announcement and/or the updated network security vulnerability testing code.

14 . The non-transitory computer readable storage medium of claim 13 , wherein scanning the one or more network comp

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Williams Aaron
• Harr Joseph
• Christensen Scott T
• Gross Ryan M

Classifications

• H04L63/1416

  Event detection, e.g. attack signature detection · CPC title

• G06N20/00

  Machine learning · CPC title

• H04L63/20

  for managing network security; network security policies in general (filtering policies H04L63/0227) · CPC title

• H04L63/1441

  Countermeasures against malicious traffic (countermeasures against attacks on cryptographic mechanisms H04L9/002) · CPC title

• H04L63/1433

  Vulnerability analysis · CPC title