Enhanced Detection of Malicious Network Traffic Using Frequency-Domain Analysis and Machine Learning Models

DOI

10.2991/978-94-6463-866-0_46How to use a DOI?

Keywords

Cybersecurity; Network Traffic Analysis; Malicious Traffic Detection; Frequency-Domain Analysis; Fast Fourier Transform (FFT); Machine Learning; XG-Boost; Support Vector Machine (SVM); Feature Extraction

Abstract

The continuous advancement of cyber threats has diminished the effectiveness of conventional network intrusion detection methods. This research proposes an innovative intrusion detection strategy that combines frequency-domain analysis with machine learning to detect harmful network traffic. By applying the Fast Fourier Transform (FFT) to the BoT-IoT dataset, spectral features are extracted from time-series traffic data. These features are then utilized to train and assess three machine learning models: XGBoost, Support Vector Machine (SVM), and Logistic Regression. Among the models, XGBoost yields a balanced F1-score of 91.2%, while SVM records the highest training accuracy at 99.6%. The findings confirm the effectiveness of using frequency-domain characteristics to improve intrusion detection performance. The approach shows strong potential for real-time implementation, with future enhancements anticipated through the integration of deep learning models and optimization algorithms.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shaik Nasir Hussain
AU  - Barigala Dhyan Susruth
AU  - V. Padmajothi
PY  - 2025
DA  - 2025/10/31
TI  - Enhanced Detection of Malicious Network Traffic Using Frequency-Domain Analysis and Machine Learning Models
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 553
EP  - 563
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_46
DO  - 10.2991/978-94-6463-866-0_46
ID  - Hussain2025
ER  -