Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Informatics Engineering and Computing
M. Hizbul Wathan
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search
Journal : International Journal of Informatics Engineering and Computing

 1 
Detection of DDoS Attacks Using Hybrid LSTM and SVM Algorithm Nahak, Ivansius; M. Hizbul Wathan
International Journal of Informatics Engineering and Computing Vol. 2 No. 2 (2025): International Journal of Informatics Engineering and Computing
Publisher : ASTEEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70687/vd7kk061

Abstract

Distributed Denial of Service (DDoS) attacks pose serious threats to network infrastructures by disrupting services through massive malicious traffic. This study proposes a hybrid detection model that integrates Long Short-Term Memory (LSTM) with a Support Vector Machine (SVM) classifier to improve the accuracy of DDoS detection in network traffic. The LSTM model captures temporal patterns within sequential traffic data, while the SVM performs the final classification to distinguish between normal and anomalous traffic. The experiment uses a dataset containing 104,345 records with 23 features that undergo preprocessing, encoding, scaling, and class balancing before model training. Experimental results demonstrate that the proposed hybrid model achieves stable learning performance with training accuracy reaching approximately 93% and validation accuracy around 94%. The loss curves show consistent decreases across 50 training epochs, indicating effective convergence and minimal overfitting. Confusion matrix analysis shows that the model correctly classifies the majority of normal and anomalous traffic samples, with relatively low false positive and false negative rates. Overall evaluation results show that the hybrid LSTM–SVM model achieves 95% accuracy with balanced classification performance. The model records strong precision, recall, and F1-score values for both normal and anomalous traffic classes.
Co-Authors Nahak, Ivansius