Building intrusion pattern miner for Snort network intrusion detection system

Abstract

In this paper, we enhance the functionalities of Snort network-based intrusion detection system to automatically generate patterns of misuse from attack data, and the ability of detecting sequential intrusion behaviors. To that, we implement an intrusion pattern discovery module which applies data mining technique to extract single intrusion patterns and sequential intrusion patterns from a collection of attack packets, and then converts the patterns to Snort detection rules for on-line intrusion detection. In order to detect sequential intrusion behavior, the Snort detection engine is accompanied with our intrusion behavior detection engine. Intrusion behavior detection engine will create an alert when a series of incoming packets match the signatures representing sequential intrusion scenarios.