Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Vokasi UNESA Bulletin of Engineering, Technology and Applied Science
Hammad, Atheer
Unknown Affiliation
Computer Science & IT Engineering Mechanical Engineering Transportation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Hybrid Deep Learning Approach for DDoS Attack Detection Based on Multidimensional Network Traffic Analysis Hammad, Atheer
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 3 No. 2 (2026): (In Progress)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v3i2.39992

Abstract

DDoS attacks have become a significant threat to the Internet of Things (IoT) and contemporary network environments due to their large traffic volume, dynamic nature, and class imbalance. Conventional intrusion detection systems may not be able to provide reliable detection in such circumstances. The proposed study is a hybrid deep learning framework that combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to identify DDoS attacks through multidimensional network traffic analysis. The CNN part is employed to derive spatial properties from traffic information, whereas the LSTM part captures temporal relationships among traffic flows. Our experimental analysis of the proposed model used an elaborate experimental setup and conventional performance measures, including accuracy, precision, recall, F1-score, and AUC. The findings of the present research indicate that the hybrid CNNLSTM model outperforms the individual CNN and LSTM models, achieving an accuracy of 99.35% and an AUC of 0.995. The strength of the proposed method in the presence of class imbalance is further confirmed by analysis using ROC and Precision-Recall curves. The results show that the suggested hybrid framework can offer a powerful and viable solution towards DDoS attack identification in IoT and next-generation networks.
Co-Authors