Visual Data Analysis for Detecting Flaws and Intruders in Computer Network Systems

To ensure the normal operation of a large computer network system, the common practice is to constantly collect system logs and analyze the network activities for detecting anomalies. Most of the analysis methods in use today are highly automated due to the enormous size of the collected data. Conventional automated methods are largely based on statistical modeling, and some employ machine learning. In this paper, we show interactive visualization as an alternative and effective data exploration method for understanding the complex behaviors of computer network systems. We describe three log-file analysis applications, and demonstrate how the use of our visualization-centered tools can lead to the discovery of flaws and intruders in the network systems