Researchers at the U.S. Army Combat Capabilities Development Command's Army Research Laboratory, working with colleagues at the University of Notre Dame and Purdue University. have developed a novel algorithm that can protect networks by detecting suspicious activity missed by current analytical methods.
Their goal was to build a higher-order network capable of identifying subtle changes in a stream of data that could indicate suspicious activity.
The researchers developed a high-order network representation, BuildHON+, reflecting real-world phenomena and scales for big data and existing network analysis tools, to perform network analytics.
Said the laboratory's Lance Kaplan, "Using a large-scale synthetic taxi movement data with 11 billion taxi movements, we show how multiple existing anomaly detection methods that depend on first-order network collectively fail to capture anomalous navigation behaviors beyond first-order, and how BuildHON+ can solve the problem."
The study was a collaboration with researchers
From "Researchers Develop Detection Method to Protect Army Networks"
U.S. Army Research Laboratory (08/17/20)
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA