# US 2020/0396243 A1 · Detection of multi-factor authentication and non-multi-factor authentication for risk assessment

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

- Number: US 2020/0396243 A1
- Document ID: US20200396243A1
- Status: Published application
- Kind: A1
- Application number: 16/904,443
- Filed: 2020-06-17
- Published: 2020-12-17
- Earliest claimed: 2019-06-17
- Assignees: CyberLucent, Inc.
- Applicants: CyberLucent Inc.
- Inventors: Michael Trentini
- Web page: https://patentgrep.com/patent/US20200396243A1

## CPC

- H04L 9/3247: {involving digital signatures}
- G06F 18/22: Matching criteria, e.g. proximity measures
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/1433: {Vulnerability analysis}
- H04L 2463/082: applying multi-factor authentication
- 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

Systems and methods are provided for determining whether or not users of a communication network are implementing Multi-Factor Authentication (MFA) when authenticating with an entity's business tools, applications, and cloud services. This information can be used as component in the calculation of a risk score that can help quantify and assess the risk posture of the entity. In some embodiments, network traffic flow metadata may be used to anonymously identify user data to assess the entity's use of MFA in determining enterprise risk that may not rely on questionnaires, surveys, manual data entry, and/or interviews. Embodiments of the application can produce a real-time analysis of the security risk of the system.

## Claims

### Claim 1

A method for determining a risk score of a communication network, the method comprising:
receiving network traffic metadata from user interactions on a user device, the network traffic metadata associated with user logins to an entity via the communication network;
constructing a plurality of digital signatures of the network traffic metadata associated with the user device, wherein the plurality of digital signatures are adjusted using a signature calculation process;
determining a first reference model for the network traffic metadata, wherein a first subset of the user logins to the entity via the communication network are associated with multi-factor authentication;
determining a second reference model for the network traffic metadata, wherein a second subset of the user logins to the entity via the communication network are associated with non-multi-factor authentication; and
calculating a risk score based on a comparison of the first subset of the user logins to the entity network and the second subset of the user logins to the entity via the communication network found in the network data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the signature calculation process is a dynamic time warping process.

### Claim 3 (depends on 1)

The method of claim 1, wherein a subset of the plurality of digital signatures are associated with an unclassified authentication process.

### Claim 4 (depends on 3)

The method of claim 3, wherein the subset of the plurality of digital signatures that are associated with the unclassified authentication process are compared with the first reference model and the second reference model using a cosine similarity process.

### Claim 5 (depends on 3)

The method of claim 3, wherein the subset of the plurality of digital signatures that are associated with the unclassified authentication process are classified as multi-factor authentication or non-multi-factor authentication based on greater similarity to the first reference model or the second reference model, respectively, or based on an absolute values of cosine calculations.

### Claim 6

A computer program product for determining a risk score of a communication network, wherein the computer program product comprises:
receiving network traffic metadata from user interactions on a user device, the network traffic metadata associated with user logins to an entity via the communication network;
constructing a plurality of digital signatures of the network traffic metadata associated with the user device, wherein the plurality of digital signatures are adjusted using a signature calculation process;
determining a first reference model for the network traffic metadata, wherein a first subset of the user logins to the entity via the communication network are associated with multi-factor authentication;
determining a second reference model for the network traffic metadata, wherein a second subset of the user logins to the entity via the communication network are associated with non-multi-factor authentication; and
calculating a risk score based on a comparison of the first subset of the user logins to the entity network and the second subset of the user logins to the entity via the communication network found in the network data.

### Claim 7 (depends on 6)

The computer program product of claim 6, wherein the signature calculation process is a dynamic time warping process.

### Claim 8 (depends on 6)

The computer program product of claim 6, wherein a subset of the plurality of digital signatures are associated with an unclassified authentication process.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the subset of the plurality of digital signatures that are associated with the unclassified authentication process are compared with the first reference model and the second reference model using a cosine similarity process.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein the subset of the plurality of digital signatures that are associated with the unclassified authentication process are classified as multi-factor authentication or non-multi-factor authentication based on greater similarity to the first reference model or the second reference model, respectively, or based on an absolute values of cosine calculations.

### Claim 11

A computer system for determining a risk score of a communication network, wherein the computer system comprises:
one or more computer processors;
one or more computer readable storage media for storing computer-implemented instructions, wherein the one or more computer processors are configured to execute the computer-implemented instructions to cause the computer system to:
receive network traffic metadata from user interactions on a user device, the network traffic metadata associated with user logins to an entity via the communication network;
construct a plurality of digital signatures of the network traffic metadata associated with the user device, wherein the plurality of digital signatures are adjusted using a signature calculation process;
determine a first reference model for the network traffic metadata, wherein a first subset of the user logins to the entity via the communication network are associated with multi-factor authentication;
determine a second reference model for the network traffic metadata, wherein a second subset of the user logins to the entity via the communication network are associated with non-multi-factor authentication; and
calculate a risk score based on a comparison of the first subset of the user logins to the entity network and the second subset of the user logins to the entity via the communication network found in the network data.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein the signature calculation process is a dynamic time warping process.

### Claim 13 (depends on 11)

The computer system of claim 11, wherein a subset of the plurality of digital signatures are associated with an unclassified authentication process.

### Claim 14 (depends on 13)

The computer system of claim 13, wherein the subset of the plurality of digital signatures that are associated with the unclassified authentication process are compared with the first reference model and the second reference model using a cosine similarity process.

### Claim 15 (depends on 13)

The computer system of claim 13, wherein the subset of the plurality of digital signatures that are associated with the unclassified authentication process are classified as multi-factor authentication or non-multi-factor authentication based on greater similarity to the first reference model or the second reference model, respectively, or based on an absolute values of cosine calculations.
