Systems and methods for artificial model building techniques

Patent metadata

Field	Value
Publication number	US-12063250-B2
Application number	US-202318094646-A
Country	US
Kind code	B2
Filing date	Jan 9, 2023
Priority date	Dec 1, 2017
Publication date	Aug 13, 2024
Grant date	Aug 13, 2024

Abstract

Embodiments disclosed describe a security awareness system may adaptively learn the best design of a simulated phishing campaign to get a user to perform the requested actions, such as clicking a hyperlink or opening a file. In some implementations, the system may adapt an ongoing campaign based on user's responses to messages in the campaign, along with the system's learned awareness. The learning process implemented by the security awareness system can be trained by observing the behavior of other users in the same company, other users in the same industry, other users that share similar attributes, all other users of the system, or users that have user attributes that match criteria set by the system, or that match attributes of a subset of other users in the system.

First claim

What is claimed is:

1. A method comprising:
establishing, by one or more processors, a model for one or more segmentations of a population responsive to selecting the model from a plurality of models based at least on the model meeting a threshold of likelihood to cause the one or more users to interact with a simulated phishing communication, the model trained with information from one or more simulated phishing campaigns;
identifying, by the one or more processors, one or more attributes of one or more users in a segmentation of the one or more segmentations;
receiving, by the one or more processors from the model, responsive to providing the one or more attributes as input to the model, information to use for a new simulated phishing campaign; and
communicating, by the one or more processors based at least on the information received from the model, at least a simulated phishing communication of the new simulated phishing campaign to one or more devices of the one or more users in the segmentation.

2. The method of claim 1 , further comprising establishing, by the one or more processors, the model responsive to selecting the model from a plurality of models that meets one or more criteria.

3. The method of claim 1 , wherein the model is further trained with information about one or more of users or accounts.

4. The method of claim 1 , wherein the model is further trained with information to highlight differences between segmentations of the population based at least on the one or more attributes.

5. The method of claim 1 , wherein the model is a persona model of one or more personas.

6. The method of claim 1 , wherein the model is further configured to output information to one of create, execute or manage the new simulated phishing campaign.

7. The method of claim 1 , wherein the information received from the model identifies a template or content of the template to use for the new simulated phishing campaign.

8. The method of claim 1 , wherein the information received from the model identifies a persona to use for the new simulated phishing campaign.

9. The method of claim 1 , wherein the segmentation of the one or more segmentations includes one of a cluster or a group in the population.

10. A system comprising:
one or more processors, coupled to memory, and configured to:
establish a model for one or more segmentations of a population responsive to selecting the model from a plurality of models based at least on the model meeting a threshold of likelihood to cause the one or more users to interact with a simulated phishing communication, the model trained with information from one or more simulated phishing campaigns;
identify, one or more attributes of one or more users in a segmentation of the one or more segmentations;
receive, from the model, responsive to providing the one or more attributes as input to the model, information to use for a new simulated phishing campaign; and
communicate, based at least on the information received from the model, at least a simulated phishing communication of the new simulated phishing campaign to one or more devices of the one or more users in the segmentation.

11. The system of claim 10 , wherein the one or more processors are further configured to establish the model responsive to selecting the model from a plurality of models that meets one or more criteria.

12. The system of claim 10 , wherein the model is further trained with information about one or more of users or accounts.

13. The system of claim 10 , wherein the model is further trained with information to highlight differences between segmentations of the population based at least on the one or more attributes.

14. The system of claim 10 , wherein the model is a persona model of one or more personas.

15. The system of claim 10 , wherein the one or more processors are further configured to use the information received from the model to one of create, execute or manage the new simulated phishing campaign.

16. The system of claim 10 , wherein the information received from the model identifies a template or content of the template to use for the new simulated phishing campaign.

17. The system of claim 10 , wherein the information received from the model identifies a persona to use for the new simulated phishing campaign.

18. The system of claim 10 , wherein the segmentation of the one or more segmentations includes one of a cluster or a group in the population.

Assignees

• Knowbe4 Inc

Inventors

• Sites Eric

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06F2221/2101

  Auditing as a secondary aspect · CPC title

• G06F21/577

  Assessing vulnerabilities and evaluating computer system security · CPC title

• G06F21/552

  involving long-term monitoring or reporting · CPC title