# US 2026/0170419 A1 · Anomaly detection based on ensemble machine learning model

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

- Number: US 2026/0170419 A1
- Document ID: US20260170419A1
- Status: Published application
- Kind: A1
- Application number: 19/352,132
- Filed: 2025-10-07
- Published: 2026-06-18
- Earliest claimed: 2015-08-31
- Assignees: Cisco Technology, Inc.
- Applicants: Cisco Technology, Inc.
- Inventors: Sudhakar Muddu; Christos Tryfonas; Joseph Auguste ZADEH; Alexander Beebe BOND; Ashwin ATHALYE
- Web page: https://patentgrep.com/patent/US20260170419A1

## CPC

- G06N 20/20: Ensemble learning
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06F 3/04847: Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
- G06F 16/24578: {using ranking}
- G06F 16/254: {Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses}
- G06F 16/285: {Clustering or classification}
- G06F 16/444: {Spatial browsing, e.g. 2D maps, 3D or virtual spaces}
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 40/134: Hyperlinking
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/04: Inference or reasoning models
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06V 10/225: {based on a marking or identifier characterising the area}
- H04L 41/0893: Assignment of logical groups to network elements
- H04L 41/145: {involving simulating, designing, planning or modelling of a network}
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04L 43/00: Arrangements for monitoring or testing data switching networks
- H04L 43/045: for graphical visualisation of monitoring data
- H04L 43/062: related to network traffic
- H04L 43/20: the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV
- H04L 63/06: {for supporting key management in a packet data network (cryptographic mechanisms or cryptographic arrangements for key management H04L9/08)}
- H04L 63/1408: {by monitoring network traffic (monitoring network traffic per se H04L43/00)}
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- H04L 63/1433: {Vulnerability analysis}
- H04L 63/1441: {Countermeasures against malicious traffic (countermeasures against attacks on cryptographic mechanisms H04L9/002)}
- H04L 63/20: {for managing network security; network security policies in general (filtering policies H04L63/0227)}
- H04L 2463/121: Timestamp
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A security platform employs a variety techniques and mechanisms to detect security related anomalies and threats in a computer network environment. The security platform is “big data” driven and employs machine learning to perform security analytics. The security platform performs user/entity behavioral analytics (UEBA) to detect the security related anomalies and threats, regardless of whether such anomalies/threats were previously known. The security platform can include both real-time and batch paths/modes for detecting anomalies and threats. By visually presenting analytical results scored with risk ratings and supporting evidence, the security platform enables network security administrators to respond to a detected anomaly or threat, and to take action promptly.

## Claims

### Claim 1

(canceled)

### Claim 2

A method comprising:
processing, by a hybrid security platform, a plurality of event data reflecting activity in a computer network to generate anomaly data, wherein the anomaly data indicates one or more variations from an expected pattern of behavior;
identifying, by a machine learning process, one or more threat indicators by processing the anomaly data, wherein a threat indicator defines a pattern of anomalous activity indicative of a potential security threat;
providing the one or more threat indicators to a threat identification process within the hybrid security platform; and
identifying a security threat by the threat identification process, the threat identification process including correlating the one or more provided threat indicators with event data to assess maliciousness.

### Claim 3 (depends on 2)

The method of claim 2, wherein the hybrid security platform includes both a platform-as-a-service (PaaS) component and a component located on a server or router outside the PaaS component.

### Claim 4 (depends on 2)

The method of claim 2, wherein processing the plurality of event data reflecting activity in a computer network to generate anomaly data includes using behavioral analysis to detect anomalous activity.

### Claim 5 (depends on 2)

The method of claim 2, wherein processing the plurality of event data reflecting activity in a computer network to generate anomaly data includes a machine learning process to detect anomalous activity.

### Claim 6 (depends on 2)

The method of claim 2, wherein the security threat identified by the threat identification process does not correspond to any previously identified signatures or rules.

### Claim 7 (depends on 2)

The method of claim 2, wherein the anomaly detection includes generating a behavioral baseline for an entity and identifying deviations from the baseline.

### Claim 8 (depends on 2)

The method of claim 2 wherein the threat identification process is performed using an ensemble of machine learning models.

### Claim 9

A hybrid security platform comprising:
one or more computing nodes, each with a processor and a memory, wherein the data intake and query system is operable to execute instructions stored in the memory, which instructions cause the computing nodes within the system to perform operations including:
processing a plurality of event data reflecting activity in a computer network to generate anomaly data, wherein the anomaly data indicates one or more variations from an expected pattern of behavior;
identifying, by a machine learning process, one or more threat indicators by processing the anomaly data, wherein a threat indicator defines a pattern of anomalous activity indicative of a potential security threat;
providing the one or more threat indicators to a threat identification process within the hybrid security platform; and
identifying a security threat by the threat identification process, the threat identification process including correlating the one or more provided threat indicators with event data to assess maliciousness.

### Claim 10 (depends on 9)

The hybrid security platform of claim 9, wherein the hybrid security platform includes both a platform-as-a-service (PaaS) component and a component located on a server or router outside the PaaS component.

### Claim 11 (depends on 9)

The hybrid security platform of claim 9, wherein processing the plurality of event data reflecting activity in a computer network to generate anomaly data includes using behavioral analysis to detect anomalous activity.

### Claim 12 (depends on 9)

The hybrid security platform of claim 9, wherein processing the plurality of event data reflecting activity in a computer network to generate anomaly data includes a machine learning process to detect anomalous activity.

### Claim 13 (depends on 9)

The hybrid security platform of claim 9, wherein the security threat identified by the threat identification process does not correspond to any previously identified signatures or rules.

### Claim 14 (depends on 9)

The hybrid security platform of claim 9, wherein the anomaly detection includes generating a behavioral baseline for an entity and identifying deviations from the baseline.

### Claim 15

A non-volatile computer-readable media including instructions, which when executed by a hybrid security platform including one or more computing nodes, each with a processor and a memory, wherein the data intake and query system is operable to execute instructions stored in the memory, which instructions cause the computing nodes within the system to perform operations including:
processing a plurality of event data reflecting activity in a computer network to generate anomaly data, wherein the anomaly data indicates one or more variations from an expected pattern of behavior;
identifying, by a machine learning process, one or more threat indicators by processing the anomaly data, wherein a threat indicator defines a pattern of anomalous activity indicative of a potential security threat;
providing the one or more threat indicators to a threat identification process within the hybrid security platform; and
identifying a security threat by the threat identification process, the threat identification process including correlating the one or more provided threat indicators with event data to assess maliciousness.

### Claim 16 (depends on 15)

The computer-readable media of claim 15, wherein the hybrid security platform includes both a platform-as-a-service (PaaS) component and a component located on a server or router outside the PaaS component.

### Claim 17 (depends on 15)

The computer-readable media of claim 15, wherein processing the plurality of event data reflecting activity in a computer network to generate anomaly data includes using behavioral analysis to detect anomalous activity.

### Claim 18 (depends on 15)

The computer-readable media of claim 15, wherein processing the plurality of event data reflecting activity in a computer network to generate anomaly data includes a machine learning process to detect anomalous activity.

### Claim 19 (depends on 15)

The computer-readable media of claim 15, wherein the security threat identified by the threat identification process does not correspond to any previously identified signatures or rules.

### Claim 20 (depends on 15)

The computer-readable media of claim 15, wherein the anomaly detection includes generating a behavioral baseline for an entity and identifying deviations from the baseline.

### Claim 21 (depends on 15)

The computer-readable media of claim 15, wherein the threat identification process is performed using an ensemble of machine learning models.
