Information-Theoretic Profiles for Intrusion Detection in LAN Traffic

摘要

In this paper, we show two methodologies for generating entropy-based behavior profiles of LAN traffic. Fast detection of intrusions caused by port scanning and worm attacks can be reached through the rate remnant elements at the packet-level, as well as the three-dimensional spaces of entropy at the flow-level. The profile was generated on LAN traffic of a campus by using empirical analysis.