Graph drawing with applications in network security

Monitoring the network activity in a continuous basis is necessary but time-consuming task. Traditionally, the monitoring process is achieved by a combination of log file analysis, traffic analysis and intrusion detection systems. Even though most systems are equipped with mechanisms that produce sufficient log files, processing the huge amount of data requires significant effort, and usually is performed with little or no automated support.

Visualization is essential in cases of large data sets such the ones produced in a network, since it interprets the huge amount of data rows into a more comprehensive visual image. Thus, by taking advantage of the human perception, the analysis of the visualization and the corresponding decision making becomes easier and more efficient. Visualizations can also be useful in fraud detection. Since bussiness anti-fraud control systems also produce textual logs in non-uniform formats, information visualization can be promising since it facilitates the quick identification of fraudulent activity.

Recent publications

E. N. Argyriou, A. Symvonis, V. Vassiliou: A Fraud Detection Visualization System Utilizing Radial Drawings and Heat-maps, In Proc. of 9th International Conference on Information Visualization Theory and Applications (IVAPP 2014), pp. 153 - 160, 2014. [PDF]

E. N. Argyriou, A. A. Sotiraki, A. Symvonis: Occupational fraud detection through visualization, In Proc. of 11th IEEE Intelligence and Security Informatics (ISI 2013), pp. 4-7, 2013. [PDF]

E. N. Argyriou, A. Symvonis: Detecting Periodicity in Serial Data through Visualization, In Proc. of 8th International Symposium on Visual Computing (ISVC 2012), Vol. 2, pp. 295-304, 2012. [PDF]