Systems and methods for determining a job score from a job title
Embodiments disclosed herein describe a server, for example a security awareness server or an artificial intelligence machine learning system that establishes a job score for a user based on the user's job title. In embodiments, the vulnerability of a user to malicious cybersecurity attacks, the propensity for the user to engage with a malicious attack, and the severity of a malicious attack likely to be sent to the user and the severity of the harm to the user's organization is the user engages with the malicious attack is represented in a user risk score. The risk score for a user of a security awareness system, or for a group of users of a security awareness system, may be calculated based on one or more of a frequency score for the user, a propensity score for the user, a severity score for the user, and a job score for the user.
1. A method of determining a job score for a user based on a job title of the user, the method comprising:
generating, by one or more servers, one or more organization graphs for one or more organizations, wherein one or more nodes of the one or more organization graphs is at least based on data for employees of the organization that identify an employee's job title, the employee's email address, and the email address of a manager of the employee;
determining, by the one or more servers, one or more centrality measures for the one or more nodes of the one or more organization graphs based at least on the data for employees;
creating, by the one or more servers responsive to determining the one or more centrality measures, for each of the one or more nodes one or more records comprising a job title and the centrality measure assigned to the job title; and
training, by the one or more servers, a model using the one or more records as input;
identifying, by the one or more servers, a user for which to determine a job score;
providing, by the one or more servers, a job title of the user as input to the model; and
receiving, by the one or more servers, the job score of the user as output from the model.
2. The method of claim 1 , wherein the one or more centrality measures comprises one of a harmonic centrality measure, a betweenness centrality measure, a degree centrality measure, a closeness centrality measure, an Eigen centrality measure, or a PageRank centrality measure.
3. The method of claim 1 , wherein the one or more centrality measures for the one or more nodes of the one or more organization graphs are determined based on a second model.
4. The method of claim 1 , wherein each of the one or more nodes of the one or more organization graphs corresponds to an employee in an organization.
5. The method of claim 1 , further comprising determining, by the one or more servers, a user risk score based on applying the job score of the user as input to a second model.
6. The method of claim 5 , further comprising using, by the one or more servers, the user risk score of the user for creating a simulated phishing communication to be communicated to a device of the user.
7. The method of claim 5 , wherein the second model is configured to take as input at least the job score of the user and provide as output the user risk score.
8. The method of claim 1 , wherein the model is retrained by the one or more servers when new input records are available.
9. The method of claim 1 , wherein the model is one of a period model or an ensemble model.
10. The method of claim 1 , wherein the model comprises an artificial intelligence model.
11. A system for determining a job score for a user based on a job title of the user, the system comprising:
one or more servers comprising one or more processors, coupled to memory and configured to:
generate one or more organization graphs for one or more organizations, wherein one or more nodes of the one or more organization graphs is at least based on data for employees of the organization that identify an employee's job title, the employee's email address, and the email address of a manager of the employee;
determine, one or more centrality measures for the one or more nodes of the one or more organization graphs based at least on the data for employees;
create, responsive to determining the one or more centrality measures, for the one or more nodes one or more records comprising a job title and the centrality measure assigned to the job title; and
train, a model using the one or more records as input;
identify a user for which to determine a job score;
provide a job title of the user as input to the model; and
receive the job score of the user as output from the model.
12. The system of claim 11 , wherein the one or more centrality measures comprises one of a harmonic centrality measure, a betweenness centrality measure, a degree centrality measure, a closeness centrality measure, an Eigen centrality measure, or a PageRank centrality measure.
13. The system of claim 11 , wherein the one or more centrality measures for the one or more organization graphs are determined based on a second model.
14. The system of claim 11 , wherein each of the one or more nodes of the one or more organization graphs corresponds to an employee in an organization.
15. The system of claim 11 , wherein the model is retrained by the one or more servers when new input records are available.
16. The system of claim 11 , wherein the one or more servers are further configured to determine a user risk score based on applying the job score of the user as input to a second model.
17. The system of claim 16 , wherein the one or more servers are further configured to use the user risk score of the user for creating a simulated phishing communication to be communicated to a device of the user.
18. The system of claim 16 , wherein the second model is configured to take as input at least the job score of the user and provide as output the user risk score.
19. The system of claim 11 , wherein the model is one of a period model or an ensemble model.
20. The system of claim 11 , wherein the model comprises an artificial intelligence model.