Evaluation of DoS/DDoS Attack Detection with ML Techniques on CIC-IDS2017 Dataset

Saida Farhat, Manel Abdelkader, Amel Meddeb-Makhlouf, Faouzi Zarai

2023

Abstract

Cloud computing is one of today’s most promising technologies. It provides its users with simplified IT infrastructure and management, remote access from effectively anywhere in the world with a stable internet connection, and cost efficiencies. Despite all these benefits, the cloud comes with some limitations and disadvantages regarding security. Denial-of-service attacks (DoS/DDoS) are one of the major security challenges in emerging cloud computing environments. In this paper, the main objective is to propose a DoS/DDoS attack detection system for Cloud environments using the most popular CICIDS2017 benchmark dataset and applying multiple Machine Learning (ML) techniques by considering both the Wednesday and Friday afternoon traffic log files. The implementation results of our model based on the eXtreme Gradient Boosting (XGBoost) algorithm demonstrate its ability to detect intrusions with a detection accuracy of 99.11% and a false alarm rate of about 0.011%.

Paper Citation

in Harvard Style

Farhat S., Abdelkader M., Meddeb-Makhlouf A. and Zarai F. (2023). Evaluation of DoS/DDoS Attack Detection with ML Techniques on CIC-IDS2017 Dataset. In Proceedings of the 9th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP, ISBN 978-989-758-624-8, pages 287-295. DOI: 10.5220/0011605700003405

in Bibtex Style

@conference{icissp23,
author={Saida Farhat and Manel Abdelkader and Amel Meddeb-Makhlouf and Faouzi Zarai},
title={Evaluation of DoS/DDoS Attack Detection with ML Techniques on CIC-IDS2017 Dataset},
booktitle={Proceedings of the 9th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,},
year={2023},
pages={287-295},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011605700003405},
isbn={978-989-758-624-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,
TI - Evaluation of DoS/DDoS Attack Detection with ML Techniques on CIC-IDS2017 Dataset
SN - 978-989-758-624-8
AU - Farhat S.
AU - Abdelkader M.
AU - Meddeb-Makhlouf A.
AU - Zarai F.
PY - 2023
SP - 287
EP - 295
DO - 10.5220/0011605700003405