Patent · US Active

Anomaly detection to identify security threats

US10673880B1 · kind B1 · utility

198Cited by

0References

29Claims

0Family size

Assignee

Splunk Inc. · US

Inventors

Robert Winslow Pratt · Woodside, US
Ravi Prasad Bulusu · San Jose, US

Key dates

Filing date	Sep 26, 2016
Grant date	Jun 2, 2020
Priority date	—
Expiry date	Mar 23, 2037

Classification

Technology area (CPC H)Electricity
CPC primaryH04L2463/121
WIPO fieldDigital communication
WIPO sectorElectrical engineering

Abstract

Techniques are described for processing anomalies detected using user-specified rules with anomalies detected using machine-learning based behavioral analysis models to identify threat indicators and security threats to a computer network. In an embodiment, anomalies are detected based on processing event data at a network security system that used rules-based anomaly detection. These rules-based detected anomalies are acquired by a network security system that uses machine-learning based anomaly detection. The rules-based detected anomalies are processed along with machine learning detected anomalies to detect threat indicators or security threats to the computer network. The threat indicators and security threats are output as alerts to the network security system that used rules-based anomaly detection.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.