Analysis of NSL-KDD Dataset for Fuzzy Based Intrusion Detection System

Macdonald Mukosera, Thabiso Peter Mpofu, Budwell Masaiti

Abstract: In a bid to provide useful information for intrusion detection; we focused on analyzing the NSL-KDD dataset. In this analysis; we seek to simplify the process of mining fuzzy rules by reducing the features and categorizing the dataset into various smaller clusters as smaller units of the dataset are easier to work with than the whole single large dataset. It is less complex to observe and discover sound fuzzy rules from a smaller dataset and this work serves as a foundation to a fuzzy logic based intrusion detection system. This paper presents a methodology for data preprocessing towards an intrusion detection system and Microsoft excel was used in the process.

Keywords: Fuzzy rules, fuzzy logic, intrusion, NSL-KDD dataset, mining