Multi-aspect visual analytics on large-scale high-dimensional cyber security data

Abstract

In this article, we present a visual analytics system, SemanticPrism, which aims to analyze large-scale highdimensional cyber security datasets containing logs of a million computers. SemanticPrism visualizes the data from three different perspectives: spatiotemporal distribution, overall temporal trends, and pixel-based IP (Internet Protocol) address blocks. With each perspective, we use semantic zooming to present more detailed information. The interlinked visualizations and multiple levels of detail allow us to detect unexpected changes taking place in different dimensions of the data and to identify potential anomalies in the network. After comparing our approach to other submissions, we outline potential paths for future improvement. Copyright © 2013 The Author(s).