A Novel Hybrid Machine Learning Approach for DoS Attack Detection

DOI

10.2991/978-94-6463-858-5_71How to use a DOI?

Keywords

Long Short Term Memory; Hybrid Model; DoS Attack Detection; Support Vector Machine; Machine Learning; Deep Learning; Network Security; Intrusion Detection System; Network Security Laboratory - Knowledge Discovery and Data Mining Dataset; Cybersecurity

Abstract

Denial of Service attacks is a substantial threat to the network security, as they overwhelm system resources and disrupt essential services. This study investigates DoS attack detection using a hybrid LSTM SVM machine learning approach, integrating Support Vector Machine and Long Short Term Memory networks. While SVM is good for the classification performance in high- dimensional spaces, LSTM excels in processing sequential data, improving detection accuracy. The hybrid SVM-LSTM model first utilizes SVM for feature extraction and probability-based predictions, which are then passed to the LSTM model for deeper sequential analysis. Key traffic features from the NSL-KDD dataset, such as packet sizes and inter-arrival times, are used for training and evaluation. The performance evaluation considers precision, accuracy, recall, and F1-score by giving a comprehensive assessment of finding capabilities. Experimental results indicate that the hybrid SVM-LSTM model achieves a remarkable 97% accuracy, exceeding the performance of standalone SVM (87%) and LSTM (95%). This accentuates the value of integrating traditional machine learning by deep learning for enhanced DoS attack detection and improved network security.

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  - Anitha Reddy
AU  - Sai Sindhu Theja
PY  - 2025
DA  - 2025/11/04
TI  - A Novel Hybrid Machine Learning Approach for DoS Attack Detection
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 839
EP  - 853
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_71
DO  - 10.2991/978-94-6463-858-5_71
ID  - Reddy2025
ER  -