# US 2019/0356679 A1 · Systems and methods for determining individual and group risk scores

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

- Number: US 2019/0356679 A1
- Document ID: US20190356679A1
- Status: Published application
- Kind: A1
- Application number: 16/413,021
- Filed: 2019-05-15
- Published: 2019-11-21
- Earliest claimed: 2018-05-16
- Assignees: KnowBe4, Inc.
- Applicants: KnowBe4, Inc.
- Inventors: Eric Sites; Greg Kras; Alin Irimie; Stu Sjouwerman; Marcio Castilho; Siegfried Martens; Eric Bonabeau; Kristian Kime
- Web page: https://patentgrep.com/patent/US20190356679A1

## CPC

- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06F 21/577: {Assessing vulnerabilities and evaluating computer system security}
- H04L 63/14: {for detecting or protecting against malicious traffic}
- H04L 63/1408: {by monitoring network traffic (monitoring network traffic per se H04L43/00)}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/1433: {Vulnerability analysis}
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Embodiments disclosed herein describe a server, for example a security awareness server or an artificial intelligence machine learning system that establishes a risk score or vulnerable for a user of a security awareness system, or for a group of users of a security awareness system. The server may create a frequency score for a user, which predicts the frequency at which the user is to be hit with a malicious attack. The frequency score may be based on at least a job score, which may be represented by a value that is based on the type of job the user has, and a breach score that may be represented by a value that is based on the user's level of exposure to email.

## Claims

### Claim 1

A method comprising:
(a) determining, by one or more servers, a frequency score to predict a frequency at which a user is to be hit with a malicious attack;
(b) determining, by the one or more servers, a propensity score that identifies a propensity of the user to respond to the hit of the malicious attack;
(c) determining, by the one or more servers, a severity score that identifies a severity of the user's response to the hit of the malicious attack;
(d) establishing, by the one or more servers, a risk score for the user based at least on the frequency score, the severity score and the propensity score; and
(e) displaying, by the one or more servers based at least on the risk score, a probability that the user will respond to a subsequent hit of a type of malicious attack at a point in time.

### Claim 2 (depends on 1)

The method of claim 1, wherein (a) further comprise determining the frequency score based at least on a job score and a breach score

### Claim 3 (depends on 2)

The method of claim 2, wherein the job score comprises a value identified based on a type of job.

### Claim 4 (depends on 2)

The method of claim 2, wherein the breach score comprises a value identified based on the user's level of exposure to email.

### Claim 5 (depends on 1)

The method of claim 1, wherein (b) further comprises determining the propensity score based at least on training a predictive model with an input of the user history of whether or not the user responded with a type of response for a given hit of the malicious attack.

### Claim 6 (depends on 1)

The method of claim 1, wherein (c) further comprises determining the severity score based at least on the job score.

### Claim 7 (depends on 1)

The method of claim 1, wherein (c) further comprises determining the severity score based at least on individual access of the user.

### Claim 8 (depends on 1)

The method of claim 1, wherein (d) further comprises establishing the risk score model as a function of the frequency score, the propensity score and the severity score.

### Claim 9 (depends on 8)

The method of claim 8, wherein the function comprises one of a weighted or logarithmic function.

### Claim 10 (depends on 1)

The method of claim 1, further comprising establishing a group risk score based on a function of risk scores of each user within the group.

### Claim 11

A system comprising:
one or more servers comprising one or more processors and configured to:
determine a frequency score to predict a frequency at which a user is to be hit with a malicious attack;
determine a propensity score that identifies a propensity of the user to respond to the hit of the malicious attack;
determine a severity score that identifies a severity of the user's response to the hit of the malicious attack;
establish a risk score for the user based at least on the frequency score, the severity score and the propensity score; and
display, based at least on the risk score, a probability that the user will respond to a subsequent hit of a type of malicious attack at a point in time.

### Claim 12 (depends on 11)

The system of claim 11, wherein the one or more servers are further configured to determine the frequency score based at least on a job score and a breach score

### Claim 13 (depends on 12)

The system of claim 12, wherein the job score comprises a value identified based on a type of job.

### Claim 14 (depends on 12)

The system of claim 12, wherein the breach score comprises a value identified based on the user's level of exposure to email.

### Claim 15 (depends on 11)

The system of claim 11, wherein the one or more servers are further configured to determine the propensity score based at least on training a predictive model with an input of the user history of whether or not the user responded with a type of response for a given hit of the malicious attack.

### Claim 16 (depends on 11)

The system of claim 11, wherein the one or more servers are further configured to determine the severity score based at least on the job score.

### Claim 17 (depends on 11)

The system of claim 11, wherein the one or more servers are further configured to determine the severity score based at least on individual access of the user.

### Claim 18 (depends on 11)

The system of claim 11, wherein the one or more servers are further configured to establish the risk score model as a function of the frequency score, the propensity score and the severity score.

### Claim 19 (depends on 18)

The system of claim 18, wherein the function comprises one of a weighted or logarithmic function.

### Claim 20 (depends on 11)

The system of claim 11, wherein the one or more servers are further configured to establish a group risk score based on a function of risk scores of each user within the group.
