Profiling internet backbone traffic: behavior models and applications

摘要: Recent spates of cyber-attacks and frequent emergence applications affecting Internet traffic dynamics have made it imperative to develop effective techniques that can extract, make sense of, significant communication patterns from data for use in network operations security management. In this paper, we present a general methodology building comprehensive behavior profiles backbone terms end-hosts services. Relying on mining information-theoretic techniques, the consists cluster extraction, automatic classification structural modeling in-depth interpretive analyses. We validate using sets core Internet. The results demonstrate indeed identify common as well anomalous are interest operators analysts.