Combating Imbalance in Network Intrusion Datasets

Free registration required

Executive Summary

An approach to combating network intrusion is the development of systems applying machine learning and data mining techniques. Many IDS (Intrusion Detection Systems) suffer from a high rate of false alarms and missed intrusions. It wanted to be able to improve the intrusion detection rate at a reduced false positive rate. The focus of this paper is rule-learning, using RIPPER, on highly imbalanced intrusion datasets with an objective to improve the true positive rate (intrusions) without significantly increasing the false positives.

  • Format: PDF
  • Size: 148.3 KB