Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights

The number of connected IoT devices is increasing significantly due to their many benefits, including automation, improved efficiency and quality of life, and reducing waste. However, these devices have several vulnerabilities that have led to the rapid growth in the number of attacks. Therefore, se...

Full description

Saved in:
Bibliographic Details
Main Authors: Filippo Genuario, Giuseppe Santoro, Michele Giliberti, Stefania Bello, Elvira Zazzera, Donato Impedovo
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/15/11/741
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850266976340934656
author Filippo Genuario
Giuseppe Santoro
Michele Giliberti
Stefania Bello
Elvira Zazzera
Donato Impedovo
author_facet Filippo Genuario
Giuseppe Santoro
Michele Giliberti
Stefania Bello
Elvira Zazzera
Donato Impedovo
author_sort Filippo Genuario
collection DOAJ
description The number of connected IoT devices is increasing significantly due to their many benefits, including automation, improved efficiency and quality of life, and reducing waste. However, these devices have several vulnerabilities that have led to the rapid growth in the number of attacks. Therefore, several machine learning-based intrusion detection system (IDS) tools have been developed to detect intrusions and suspicious activity to and from a host (HIDS—Host IDS) or, in general, within the traffic of a network (NIDS—Network IDS). The proposed work performs a comparative analysis and an ablative study among recent machine learning-based NIDSs to develop a benchmark of the different proposed strategies. The proposed work compares both shallow learning algorithms, such as decision trees, random forests, Naïve Bayes, logistic regression, XGBoost, and support vector machines, and deep learning algorithms, such as DNNs, CNNs, and LSTM, whose approach is relatively new in the literature. Also, the ensembles are tested. The algorithms are evaluated on the KDD-99, NSL-KDD, UNSW-NB15, IoT-23, and UNB-CIC IoT 2023 datasets. The results show that the NIDS tools based on deep learning approaches achieve better performance in detecting network anomalies than shallow learning approaches, and ensembles outperform all the other models.
format Article
id doaj-art-e33e83deef3043fa8b14d489612cf99c
institution OA Journals
issn 2078-2489
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-e33e83deef3043fa8b14d489612cf99c2025-08-20T01:54:01ZengMDPI AGInformation2078-24892024-11-01151174110.3390/info15110741Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and InsightsFilippo Genuario0Giuseppe Santoro1Michele Giliberti2Stefania Bello3Elvira Zazzera4Donato Impedovo5Invest & Engineering S.r.l., Viale Paolo Borsellino e Giovanni Falcone, 17, 70125 Bari, BA, ItalyInvest & Engineering S.r.l., Viale Paolo Borsellino e Giovanni Falcone, 17, 70125 Bari, BA, ItalyInvest & Engineering S.r.l., Viale Paolo Borsellino e Giovanni Falcone, 17, 70125 Bari, BA, ItalyDigital Innovation S.r.l., Via Edoardo Orabona, 4, 70125 Bari, BA, ItalyKad3 S.r.l., Via Baione, snc, 70043 Monopoli, BA, ItalyDepartment of Computer Science, University of Bari “Aldo Moro”, Piazza Umberto I, 1, 70121 Bari, BA, ItalyThe number of connected IoT devices is increasing significantly due to their many benefits, including automation, improved efficiency and quality of life, and reducing waste. However, these devices have several vulnerabilities that have led to the rapid growth in the number of attacks. Therefore, several machine learning-based intrusion detection system (IDS) tools have been developed to detect intrusions and suspicious activity to and from a host (HIDS—Host IDS) or, in general, within the traffic of a network (NIDS—Network IDS). The proposed work performs a comparative analysis and an ablative study among recent machine learning-based NIDSs to develop a benchmark of the different proposed strategies. The proposed work compares both shallow learning algorithms, such as decision trees, random forests, Naïve Bayes, logistic regression, XGBoost, and support vector machines, and deep learning algorithms, such as DNNs, CNNs, and LSTM, whose approach is relatively new in the literature. Also, the ensembles are tested. The algorithms are evaluated on the KDD-99, NSL-KDD, UNSW-NB15, IoT-23, and UNB-CIC IoT 2023 datasets. The results show that the NIDS tools based on deep learning approaches achieve better performance in detecting network anomalies than shallow learning approaches, and ensembles outperform all the other models.https://www.mdpi.com/2078-2489/15/11/741intrusion detection systemsnetwork traffic monitoringcyber-attack monitoringmachine learningdeep learning
spellingShingle Filippo Genuario
Giuseppe Santoro
Michele Giliberti
Stefania Bello
Elvira Zazzera
Donato Impedovo
Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights
Information
intrusion detection systems
network traffic monitoring
cyber-attack monitoring
machine learning
deep learning
title Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights
title_full Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights
title_fullStr Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights
title_full_unstemmed Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights
title_short Machine Learning-Based Methodologies for Cyber-Attacks and Network Traffic Monitoring: A Review and Insights
title_sort machine learning based methodologies for cyber attacks and network traffic monitoring a review and insights
topic intrusion detection systems
network traffic monitoring
cyber-attack monitoring
machine learning
deep learning
url https://www.mdpi.com/2078-2489/15/11/741
work_keys_str_mv AT filippogenuario machinelearningbasedmethodologiesforcyberattacksandnetworktrafficmonitoringareviewandinsights
AT giuseppesantoro machinelearningbasedmethodologiesforcyberattacksandnetworktrafficmonitoringareviewandinsights
AT michelegiliberti machinelearningbasedmethodologiesforcyberattacksandnetworktrafficmonitoringareviewandinsights
AT stefaniabello machinelearningbasedmethodologiesforcyberattacksandnetworktrafficmonitoringareviewandinsights
AT elvirazazzera machinelearningbasedmethodologiesforcyberattacksandnetworktrafficmonitoringareviewandinsights
AT donatoimpedovo machinelearningbasedmethodologiesforcyberattacksandnetworktrafficmonitoringareviewandinsights