Flow Exporter Impact on Intelligent Intrusion Detection Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pinto, Daniela, Vitorino, João, Maia, Eva, Amorim, Ivone, Praça, Isabel
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912160783794176
author Pinto, Daniela
Vitorino, João
Maia, Eva
Amorim, Ivone
Praça, Isabel
author_facet Pinto, Daniela
Vitorino, João
Maia, Eva
Amorim, Ivone
Praça, Isabel
contents High-quality datasets are critical for training machine learning models, as inconsistencies in feature generation can hinder the accuracy and reliability of threat detection. For this reason, ensuring the quality of the data in network intrusion detection datasets is important. A key component of this is using reliable tools to generate the flows and features present in the datasets. This paper investigates the impact of flow exporters on the performance and reliability of machine learning models for intrusion detection. Using HERA, a tool designed to export flows and extract features, the raw network packets of two widely used datasets, UNSW-NB15 and CIC-IDS2017, were processed from PCAP files to generate new versions of these datasets. These were compared to the original ones in terms of their influence on the performance of several models, including Random Forest, XGBoost, LightGBM, and Explainable Boosting Machine. The results obtained were significant. Models trained on the HERA version of the datasets consistently outperformed those trained on the original dataset, showing improvements in accuracy and indicating a better generalisation. This highlighted the importance of flow generation in the model's ability to differentiate between benign and malicious traffic.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14021
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Flow Exporter Impact on Intelligent Intrusion Detection Systems
Pinto, Daniela
Vitorino, João
Maia, Eva
Amorim, Ivone
Praça, Isabel
Cryptography and Security
Machine Learning
High-quality datasets are critical for training machine learning models, as inconsistencies in feature generation can hinder the accuracy and reliability of threat detection. For this reason, ensuring the quality of the data in network intrusion detection datasets is important. A key component of this is using reliable tools to generate the flows and features present in the datasets. This paper investigates the impact of flow exporters on the performance and reliability of machine learning models for intrusion detection. Using HERA, a tool designed to export flows and extract features, the raw network packets of two widely used datasets, UNSW-NB15 and CIC-IDS2017, were processed from PCAP files to generate new versions of these datasets. These were compared to the original ones in terms of their influence on the performance of several models, including Random Forest, XGBoost, LightGBM, and Explainable Boosting Machine. The results obtained were significant. Models trained on the HERA version of the datasets consistently outperformed those trained on the original dataset, showing improvements in accuracy and indicating a better generalisation. This highlighted the importance of flow generation in the model's ability to differentiate between benign and malicious traffic.
title Flow Exporter Impact on Intelligent Intrusion Detection Systems
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2412.14021