Combining visual and automated data mining for near-real-time anomaly detection and analysis in BGP

摘要

This volume contains the papers presented at the CCS Workshop on Visualization and Data Mining for Computer Security. VizSec/DMSec 2004 was held on October 29th, 2004 at George Mason University in conjunction with the Eleventh ACM Conference on Computer and Communications Security. >Information about security on large and complex computer networks is high volume, heterogeneous, distributed, and dynamic over time. This workshop brought together researchers from two complementary approaches for processing high-dimensional data into knowledge: visualization and data mining. Visualization represents high-dimension security data in 2D/3D graphics and animations intended to facilitate quick inferences for situational awareness and focusing of attention on potential security events. Data mining focuses on algorithms to accurately detect patterns in high-dimension security data representing unauthorized system access or computer network attacks. The workshop received 36 paper submissions, from which the 13 long and 6 short papers that appear here were selected by the program committee.