# US 2020/0287922 A1 · Anomaly detection for a networking device based on monitoring related sets of counters

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

- Number: US 2020/0287922 A1
- Document ID: US20200287922A1
- Status: Published application
- Kind: A1
- Application number: 16/296,373
- Filed: 2019-03-08
- Published: 2020-09-10
- Earliest claimed: 2019-03-08
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Pengywan Wang; Brian Weis
- Web page: https://patentgrep.com/patent/US20200287922A1

## CPC

- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06F 21/552: {involving long-term monitoring or reporting}
- G06N 20/00: Machine learning
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In one embodiment, a monitoring process identifies a set of counters maintained by a networking device by comparing a configuration of the networking device to an object relationship model. The monitoring process obtains counter values from the identified set of counters maintained by the networking device. The monitoring process detects an anomaly by using the obtained counter values as input to a machine learning-based anomaly detector. The monitoring process generates an anomaly detection alert for the detected anomaly.

## Claims

### Claim 1

A method comprising:
identifying, by a monitoring process, a set of counters maintained by a networking device by comparing a configuration of the networking device to an object relationship model;
obtaining, by the monitoring process, counter values from the identified set of counters maintained by the networking device;
detecting, by the monitoring process, an anomaly by using the obtained counter values as input to a machine learning-based anomaly detector; and
generating, by the monitoring process, an anomaly detection alert for the detected anomaly.

### Claim 2 (depends on 1)

The method as in claim 1, further comprising:
determining, by the monitoring process, that the detected anomaly is caused by a network attack, wherein the generated anomaly detection alert is indicative of the network attack.

### Claim 3 (depends on 1)

The method as in claim 1, wherein the networking device comprises a network switch, a network router, or a network firewall.

### Claim 4 (depends on 1)

The method as in claim 1, wherein a particular counter in the set of counters is associated with an interface of the networking device and indicative of one of: a count of packets received on the interface, a count of bytes received on the interface, a count of cyclical redundancy check (CRC) errors on the interface, a number of resets or restarts of the interface, or a number of output errors for the interface.

### Claim 5 (depends on 1)

The method as in claim 1, wherein the object relationship model specifies parent-child dependencies between the counters whereby a parent counter being incremented is a prerequisite for its child counter being incremented.

### Claim 6 (depends on 1)

The method as in claim 1, wherein the object relationship model maps the configuration of the networking device to configuration instance objects, and wherein a particular configuration instance object is associated with one or more of the counters.

### Claim 7 (depends on 6)

The method as in claim 6, wherein the object relationship model represents resources of the networking device as resource objects and relates the resource objects to the configuration instance objects.

### Claim 8 (depends on 1)

The method as in claim 1, wherein the monitoring process is executed by the networking device.

### Claim 9

An apparatus, comprising:
one or more network interfaces to communicate with a network;
a processor coupled to the network interfaces and configured to execute one or more processes; and
a memory configured to store a process executable by the processor, the process when executed configured to:
identify a set of counters maintained by a networking device by comparing a configuration of the networking device to an object relationship model;
obtain counter values from the identified set of counters maintained by the networking device;
detect an anomaly by using the obtained counter values as input to a machine learning-based anomaly detector; and
generate an anomaly detection alert for the detected anomaly.

### Claim 10 (depends on 9)

The apparatus as in claim 9, wherein the process when executed is further configured to:
determine that the detected anomaly is caused by a network attack, wherein the generated anomaly detection alert is indicative of the network attack.

### Claim 11 (depends on 9)

The apparatus as in claim 9, wherein the networking device comprises a network switch, a network router, or a network firewall.

### Claim 12 (depends on 9)

The apparatus as in claim 9, wherein a particular counter in the set of counters is associated with an interface of the networking device and indicative of one of: a count of packets received on the interface, a count of bytes received on the interface, a count of cyclical redundancy check (CRC) errors on the interface, a number of resets or restarts of the interface, or a number of output errors for the interface.

### Claim 13 (depends on 9)

The apparatus as in claim 9, wherein the object relationship model specifies parent-child dependencies between the counters whereby a parent counter being incremented is a prerequisite for its child counter being incremented.

### Claim 14 (depends on 9)

The apparatus as in claim 9, wherein the object relationship model maps the configuration of the networking device to configuration instance objects, and wherein a particular configuration instance object is associated with one or more of the counters.

### Claim 15 (depends on 14)

The apparatus as in claim 14, wherein the object relationship model represents resources of the networking device as resource objects and relates the resource objects to the configuration instance objects.

### Claim 16 (depends on 9)

The apparatus as in claim 9, wherein the apparatus comprises the networking device.

### Claim 17

A tangible, non-transitory, computer-readable medium storing program instructions that cause a monitoring service to execute a process comprising:
identifying, by the monitoring process, a set of counters maintained by a networking device by comparing a configuration of the networking device to an object relationship model;
obtaining, by the monitoring process, counter values from the identified set of counters maintained by the networking device;
detecting, by the monitoring process, an anomaly by using the obtained counter values as input to a machine learning-based anomaly detector; and
generating, by the monitoring process, an anomaly detection alert for the detected anomaly.

### Claim 18 (depends on 17)

The computer-readable medium as in claim 17, wherein the process further comprises:
determining, by the monitoring process, that the detected anomaly is caused by a network attack, wherein the generated anomaly detection alert is indicative of the network attack.

### Claim 19 (depends on 17)

The computer-readable medium as in claim 17, wherein the networking device comprises a network switch, a network router, or a network firewall.

### Claim 20 (depends on 17)

The computer-readable medium as in claim 17, wherein the object relationship model specifies parent-child dependencies between the counters whereby a parent counter being incremented is a prerequisite for its child counter being incremented.
