# US 2021/0344573 A1 · Automatically detecting authorized remote administration sessions in a network monitoring system

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

- Number: US 2021/0344573 A1
- Document ID: US20210344573A1
- Status: Published application
- Kind: A1
- Application number: 17/376,924
- Filed: 2021-07-15
- Published: 2021-11-04
- Earliest claimed: 2017-12-20
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: David McGrew; Martin Rehak; Blake Harrell Anderson; Sunil Amin
- Web page: https://patentgrep.com/patent/US20210344573A1

## CPC

- G06F 21/554: {involving event detection and direct action}
- H04L 41/28: Restricting access to network management systems or functions, e.g. using authorisation function to access network configuration
- G06F 21/55: Detecting local intrusion or implementing counter-measures
- H04L 63/14: {for detecting or protecting against malicious traffic}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/1441: {Countermeasures against malicious traffic (countermeasures against attacks on cryptographic mechanisms H04L9/002)}
- H04W 12/12: Detection or prevention of fraud
- H04W 12/121: Wireless intrusion detection systems [WIDS]; Wireless intrusion prevention systems [WIPS]
- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- H04L 67/143: Termination or inactivation of sessions, e.g. event-controlled end of session
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

In one embodiment, a service receives administration traffic data in a network associated with a remote administration session in which a control device remotely administers a client device. The service analyzes the administration traffic data to determine whether any portion of the administration traffic data is resulting from an administration session involving a trusted administrator. The service flags a first portion of the administration traffic data as authorized when the first portion of the administration traffic data is determined to result from an administration session involving a trusted administrator, and a second portion of the administration traffic data is non-flagged. The service assesses the second portion of the administration traffic data using a machine learning-based traffic classifier to determine whether the second portion of the administration traffic data is malicious.

## Claims

### Claim 1

A method comprising:
receiving, at a service, administration traffic data in a network associated with a remote administration session in which a control device remotely administers a client device;
analyzing, by the service, the administration traffic data to determine whether any portion of the administration traffic data is resulting from an administration session involving a trusted administrator;
flagging, by the service and based on analyzing the administration traffic data, a first portion of the administration traffic data as authorized when the first portion of the administration traffic data is determined to result from an administration session involving a trusted administrator, wherein a second portion of the administration traffic data is non-flagged; and
assessing, by the service, the second portion of the administration traffic data that is non-flagged using a machine learning-based traffic classifier that is trained to is distinguish between benign traffic and malicious traffic in the network to determine whether the second portion of the administration traffic data that is non-flagged is malicious,
wherein the first portion of the administration traffic data that is flagged as authorized is excluded from assessment using the machine learning-based traffic classifier.

### Claim 2 (depends on 1)

The method as in claim 1, wherein analyzing the administration traffic data comprises:
determining, by the service, that the control device was operated by the trusted administrator during the remote administration session.

### Claim 3 (depends on 1)

The method as in claim 1, wherein at least a portion of the administration traffic data comprises data generated by a monitoring process executed by the control device.

### Claim 4 (depends on 3)

The method as in claim 3, wherein at least a portion of the administration traffic data comprises data generated by a network traffic monitor between the control device and the client device in the network, and wherein analyzing the administration traffic data comprises:
matching, by the service, a network address captured by the monitoring process executed by the control device to a network address captured by the network traffic monitor.

### Claim 5 (depends on 3)

The method as in claim 3, wherein analyzing the administration traffic data comprises:
identifying, by the service and from the data generated by the monitoring process executed by the control device, a particular process that was executed by the control device to initiate the remote administration session with the client device; and
determining, by the service, whether the particular process is authorized.

### Claim 6 (depends on 1)

The method as in claim 1, wherein the machine learning-based traffic classifier is trained using the first portion of the administration traffic data that is flagged as authorized.

### Claim 7 (depends on 1)

The method as in claim 1, wherein the machine learning-based traffic classifier is trained using samples of benign traffic and malicious traffic.

### Claim 8 (depends on 1)

The method as in claim 1, wherein the malicious traffic is indicative of malfeasance by the trusted administrator in the network.

### Claim 9 (depends on 1)

The method as in claim 1, wherein the remote administration session comprises at least one of: a remote desktop administration session, a Secure Shell (SSH) session, or Secure Copy (SCP) session.

### Claim 10

An apparatus, comprising:
one or more network interfaces to communicate with a network;
a processor coupled to the one or more network interfaces and configured to execute one or more operations; and
a memory configured to store a process that is executable by the processor, the process when executed configured to:
receive administration traffic data in a network associated with a remote administration session in which a control device remotely administers a client device;
analyze the administration traffic data to determine whether any portion of the administration traffic data is resulting from an administration session involving a trusted administrator;
flag, based on analyzing the administration traffic data, a first portion of the administration traffic data as authorized when the first portion of the administration traffic data is determined to result from an administration session involving a trusted administrator, wherein a second portion of the administration traffic data is non-flagged; and
assess the second portion of the administration traffic data that is non-flagged using a machine learning-based traffic classifier that is trained to distinguish between benign traffic and malicious traffic in the network to determine whether the second portion of the administration traffic data that is non-flagged is malicious,
wherein the first portion of the administration traffic data that is flagged as authorized is excluded from assessment using the machine learning-based traffic classifier.

### Claim 11 (depends on 10)

The apparatus as in claim 10, wherein the apparatus analyzes the administration traffic data by:
determining that the control device was operated by the trusted administrator during the remote administration session.

### Claim 12 (depends on 10)

The apparatus as in claim 10, wherein at least a portion of the administration traffic data comprises data generated by a monitoring process executed by the control device.

### Claim 13 (depends on 12)

The apparatus as in claim 12, wherein at least a portion of the administration traffic data comprises data generated by a network traffic monitor between the control device and the client device in the network, and wherein the apparatus analyzes the administration traffic data by:
matching a network address captured by the monitoring process executed by the control device to a network address captured by the network traffic monitor.

### Claim 14 (depends on 12)

The apparatus as in claim 12, wherein the apparatus analyzes the administration traffic data by:
identifying, from the data generated by the monitoring process executed by the control device, a particular process that was executed by the control device to initiate the remote administration session with the client device; and
determining whether the particular process is authorized.

### Claim 15 (depends on 10)

The apparatus as in claim 10, wherein the machine learning-based traffic classifier is trained using the first portion of the administration traffic data that is flagged as authorized.

### Claim 16 (depends on 10)

The apparatus as in claim 10, wherein the machine learning-based traffic classifier is trained using samples of benign traffic and malicious traffic.

### Claim 17 (depends on 10)

The apparatus as in claim 10, wherein the malicious traffic is indicative of malfeasance by the trusted administrator in the network.

### Claim 18 (depends on 10)

The apparatus as in claim 10, wherein the remote administration session comprises at least one of: a remote desktop administration session, a Secure Shell (SSH) session, or Secure Copy (SCP) session.

### Claim 19

A tangible, non-transitory, computer-readable medium that program instructions that cause a device to execute a process comprising:
receiving administration traffic data in a network associated with a remote administration session in which a control device remotely administers a client device;
analyzing the administration traffic data to determine whether any portion of the administration traffic data is resulting from an administration session involving a trusted administrator;
flagging, based on analyzing the administration traffic data, a first portion of the administration traffic data as authorized when the first portion of the administration traffic data is determined to result from an administration session involving a trusted administrator, wherein a second portion of the administration traffic data is non-flagged; and
assessing the second portion of the administration traffic data that is non-flagged using a machine learning-based traffic classifier that is trained to distinguish between benign traffic and malicious traffic in the network to determine whether the second portion of the administration traffic data that is non-flagged is malicious,
wherein the first portion of the administration traffic data that is flagged as authorized is excluded from assessment using the machine learning-based traffic classifier.

### Claim 20 (depends on 19)

The tangible, non-transitory, computer-readable medium as in claim 19, wherein analyzing the administration traffic data comprises:
determining that the control device was operated by an authorized administrator during the remote administration session.
