Systems and methods for AIDA based grouping
The present disclosure describes systems and methods for dynamically creating groups of users based on attributes for simulated phishing campaign. A campaign controller determines one or more attributes of a plurality of users during execution of a simulated phishing campaign and creates one or more groups of users during based on the identified attributes. The campaign controller selects a template to be used to execute a portion of the simulated phishing campaign for a first group of users and then communicates one or more simulated phishing communications to the first group of users according to the template. The template may identify a list of a plurality of types of simulated phishing communications (email, text or SMS message, phone call or Internet based communication) and at least a portion of the content for the simulated phishing communication.
1. A method comprising:
creating, by a device, a first group of users and a second group of users from a plurality of users based at least on results from a plurality of simulated phishing communications;
receiving, by the device during execution of one or more simulated phishing campaigns comprising the plurality of simulated phishing communications, identification by a model of a first template to use for the first group of users and a second template to use for the second group of users, the model trained via machine learning using results from the plurality of simulated phishing communications, the model trained to identify a template having a predetermined likelihood of a group of users to take a predetermined action; and
communicating, by the device, one or more simulated phishing communications to the first group of users according to the first template and to the second group of users according to the second template during the one or more simulated phishing campaigns.
2. The method of claim 1 , further comprising creating, by the device, the first group of users and the second group of users based at least on one or more attributes of the plurality of users.
3. The method of claim 2 , wherein the one or more attributes of the plurality of users comprises one or more of the following: a geographic region, a demographic, or an organizational level within a company.
4. The method of claim 1 , further comprising determining, by the device, one or more attributes of each of the plurality users during execution of one or more simulated phishing campaigns comprising the plurality of simulated phishing communications.
5. The method of claim 1 , further comprising selecting by the model the first template from the plurality of templates as output to the model responsive to an input to the model of one or more attributes of the first group of users.
6. The method of claim 1 , further comprising selecting by the model the second template from the plurality of templates as output to the model responsive to an input to the model of one or more attributes of the second group of users.
7. The method of claim 1 , wherein the model is trained by applying machine learning to the results from the plurality of simulated phishing communications and one or more attributes of the plurality of users.
8. The method of claim 1 , wherein the model is further configured to identify for the first group of users the first template having a predetermined likelihood of the first group of users to take a predetermined action and to identify for the second group of users the second template having the predetermined likelihood of the second group of users to take the predetermined action.
9. A system comprising:
one or more processors, coupled to memory, and configured to:
create a first group of users and a second group of users from a plurality of users based at least on results from a plurality of simulated phishing communications;
receive identification, during execution of one or more simulated phishing campaigns comprising the plurality of simulated phishing communications, by a model of a first template to use for the first group of users and a second template to use for the second group of users, the model trained via machine learning using results from the plurality of simulated phishing communications to identify a template having a predetermined likelihood of a group of users to take a predetermined action; and
communicate one or more simulated phishing communications to the first group of users according to the first template and to the second group of users according to the second template during the one or more simulated phishing campaigns.
10. The system of claim 9 , wherein the one or more processors are further configured to create the first group of users and the second group of users based at least on one or more attributes of the plurality of users.
11. The system of claim 10 , wherein the one or more attributes of the plurality of users comprises one or more of the following: a geographic region, a demographic, or an organizational level within a company.
12. The system of claim 9 , wherein the one or more processors are further configured to determine one or more attributes of each of the plurality user during execution of one or more simulated phishing campaigns comprising the plurality of simulated phishing communications.
13. The system of claim 9 , wherein the model is further configured to select the first template from the plurality of templates as output to the model responsive to an input to the model of one or more attributes of the first group of users.
14. The system of claim 9 , wherein the model is further configured the second template from the plurality of templates as output to the model responsive to an input to the model of one or more attributes of the second group of users.
15. The system of claim 9 , wherein the model is trained by applying machine learning to the results from the plurality of simulated phishing communications and one or more attributes of the plurality of users.
16. The system of claim 9 , wherein the model is further configured to identify for the first group of users the first template having a predetermined likelihood of the first group of users to take a predetermined action and to identify for the second group of users the second template having the predetermined likelihood of the second group of users to take the predetermined action.