Classification Hardness for Supervised Learners on 20 Years of Intrusion Detection Data

This article consolidates analysis of established (NSL-KDD) and new intrusion detection datasets (ISCXIDS2012, CICIDS2017, CICIDS2018) through the use of supervised machine learning (ML) algorithms. The uniformity in analysis procedure opens up the option to compare the obtained results. It also provides a stronger foundation for the conclusions about the efficacy of supervised learners on the main classification task in network security. This research is motivated in part to address the lack of adoption of these modern datasets. Starting with a broad scope that includes classification by algorithms from different families on both established and new datasets has been done to expand the existing foundation and reveal the most opportune avenues for further inquiry. After obtaining baseline results, the classification task was increased in difficulty, by reducing the available data to learn from, both horizontally and vertically. The data reduction has been included as a stress-test to verify if the very high baseline results hold up under increasingly harsh constraints. Ultimately, this work contains the most comprehensive set of results on the topic of intrusion detection through supervised machine learning. Researchers working on algorithmic improvements can compare their results to this collection, knowing that all results reported here were gathered through a uniform framework. This work's main contributions are the outstanding classification results on the current state of the art datasets for intrusion detection and the conclusion that these methods show remarkable resilience in classification performance even when aggressively reducing the amount of data to learn from.