Advancing Network Anomaly Detection Using Deep Learning and Federated Learning in an Interconnected Environment

Hanen Dhrir, Maha Charfeddine, Habib M. Kammoun

2025

Abstract

Network anomaly detection is a fundamental cybersecurity task that seeks to identify unusual patterns that could indicate security threats or system failures. Traditional centralized anomaly detection methods face issues such as data privacy. Federated Learning has emerged as a promising solution that distributes model training across multiple devices or nodes. Federated Learning improves anomaly detection by leveraging geographically distributed data sources while maintaining data privacy and security. This study presents a novel Federated Learning architecture designed specifically for network anomaly detection, addressing important information sensitivity issues in network environments. We compare some Deep Learning algorithms, such as Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Multilayer Perceptron (MLP), using XGBoost for feature selection and Stochastic Gradient Descent (SGD) as an optimizer. To address the problem of imbalanced data, we use the Synthetic Minority Over-sampling Technique (SMOTE) with the UNSW-NB15 dataset. Our methodology is rigorously evaluated using standard evaluation metrics and compared to state-of-the-art approaches.

Paper Citation

in Harvard Style

Dhrir H., Charfeddine M. and Kammoun H. (2025). Advancing Network Anomaly Detection Using Deep Learning and Federated Learning in an Interconnected Environment. In Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE; ISBN 978-989-758-742-9, SciTePress, pages 343-350. DOI: 10.5220/0013134100003928

in Bibtex Style

@conference{enase25,
author={Hanen Dhrir and Maha Charfeddine and Habib Kammoun},
title={Advancing Network Anomaly Detection Using Deep Learning and Federated Learning in an Interconnected Environment},
booktitle={Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE},
year={2025},
pages={343-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013134100003928},
isbn={978-989-758-742-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE
TI - Advancing Network Anomaly Detection Using Deep Learning and Federated Learning in an Interconnected Environment
SN - 978-989-758-742-9
AU - Dhrir H.
AU - Charfeddine M.
AU - Kammoun H.
PY - 2025
SP - 343
EP - 350
DO - 10.5220/0013134100003928
PB - SciTePress