A Comparative Study on Contemporary Intrusion Detection Datasets for Machine Learning Research
Smirti Dwibedi, Medha Pujari, Weiqing Sun
Abstract
In the modern world, Machine Learning (ML) touches our day-to-day routine in various ways. Researchers have been actively working on adding intelligence to Intrusion Detection Systems (IDSs) using ML techniques because a traditional IDS can detect known attacks but is incapable of detecting unknown attacks. Two major factors on which the efficiency of an intelligent IDS model depends are - the data and the mechanism used by the model to learn the data. This paper focuses on the contribution of data, by performing an analysis of recently published datasets, namely, UNSW-NB15, Bot-IoT, and CSE-CIC-IDS2018, employing ML algorithms including Random Forest (RF), Support Vector Machines (SVMs), Keras Deep Learning models, and XGBoost. The paper compares the performance of an ML-based IDS by training it with each of them, thereby, analyzing how the choice of a dataset impacts the performance.