A Hybrid Transformer-Based Deep Neural Network for DDoS Detection: A Comparative Evaluation Across Modern Architectures

Article Sidebar

PDF
Published: Oct 18, 2025
DOI: https://doi.org/10.37936/ecti-cit.2025194.263424
Keywords:
DDoS Detection Deep Learning Transformer Attention Mechanism Model Comparison Cyber Threat Mitigation

Main Article Content

Nitipon Pongphaw
Kasetsart University Chalermphrakiat Sakon Nakhon Province Campus, Thailand
Mune Sukumaradat
Kasetsart University Chalermphrakiat Sakon Nakhon Province Campus, Thailand
Prommin Buaphan
Kasetsart University Chalermphrakiat Sakon Nakhon Province Campus, Thailand

Abstract

DDoS attacks remain a major threat to network infrastructures. While deep learning is applied for detection, prior studies often lack standardized comparison and stability evaluation under consistent settings. This study systematically evaluates nine deep learning models including MLP, CNNs, ResNet1D, and attention-augmented architectures under consistent experimental settings and introduces two novel models: TDNN (Transformer-based) and ATDNN (attention-enhanced) for capturing complex traffic patterns. Using a balanced real-world dataset, all models were trained over five independent runs, with performance assessed via accuracy, precision, recall, and F1-score. TDNN achieved the highest performance (Accuracy: 0.9653 ±0.0018; Precision: 0.9659 ±0.0016; Recall: 0.9653 ±0.0018; F1-score: 0.9653 ±0.0018), while simpler models such as DNN, MLP, and LSTMClassier also performed competitively with lower variance. The study further analyzes learning behaviors and evaluates deployment potential, highlighting that well-tuned deep learning models, particularly TDNN, can support real-time DDoS detection in enterprise and edge computing environments.

Article Details

How to Cite
[1]
N. Pongphaw, M. Sukumaradat, and P. Buaphan, “A Hybrid Transformer-Based Deep Neural Network for DDoS Detection: A Comparative Evaluation Across Modern Architectures”, ECTI-CIT Transactions, vol. 19, no. 4, pp. 609–620, Oct. 2025.
Issue
Vol. 19 No. 4 (2025): ECTI Transactions on CIT (Oct 2025)
Section
Research Article
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Author Biography

Nitipon Pongphaw, Kasetsart University Chalermphrakiat Sakon Nakhon Province Campus, Thailand

Nitipon Pongphaw is currently pursuing a Bachelor's degree in Computer Engineering. His academic interests and expertise lie in the areas of Machine Learning (ML), Deep Learning (DL), and adaptive systems, with a particular focus on their application to dynamic and high-variability domains. He has experience developing and evaluating intelligent models for network security and anomaly detection. His work reflects a strong interest in leveraging artificial intelligence to create scalable and efficient solutions for real-world problems.

References

A. Otiko, E. Edim, G. Iyang and E. Oyo-Ita, “A survey of AI methods for detection of DDoS attacks on networks,” Advances in Research, vol. 25, no. 5, pp. 256–271, 2024.

M. Prabha and B. Srinivasan, “Enhanced DDoS attack detection using improved deep convolutional neural networks,” International Journal of Progressive Research in Engineering Management and Science, 2024.

M. Ramzan et al., “Distributed denial of service attack detection in network traffic using deep learning algorithm,” Sensors, vol. 23, no. 20, p. 8642, 2023.

H. Xu and H. Xian, “SCD: A detection system for DDoS attacks based on SAE-CNN networks,” Frontiers in Computing and Intelligent Systems, vol. 5, no. 3, pp. 94–99, 2023.

N. Patil, C. Krishna and K. Kumar, “SSKDDoS: Distributed stream processing framework based classification system for DDoS attacks,” Cluster Computing, vol. 25, no. 2, pp. 1355–1372, 2022.

N. Katuk, M. Sinal, M. Alsamman and I. Ahmad, “An observational mechanism for detection of distributed denial-of-service attacks,” International Journal of Advances in Applied Sciences, vol. 12, no. 2, pp. 121–132, 2023.

M. Owaid and A. Hammoodi, “Evaluating machine learning and deep learning models for enhanced DDoS attack detection,” Mathematical Modelling and Engineering Problems, vol. 11, no. 2, pp. 493–499, 2024.

F. Alanazi, K. Jambi, F. Eassa, M. Khemakhem, A. Basuhail and K. Alsubhi, “Ensemble deep learning models for mitigating DDoS attack in software-defined network,” Intelligent Automation & Soft Computing, vol. 33, no. 2, pp. 923–938, 2022.

E. Effah, E. Osei, M. Dorgbefu and A. Tetteh, “Hybrid approach to classification of DDoS attacks on a computer network infrastructure,” Asian Journal of Research in Computer Science, vol. 17, no. 4, pp. 19–43, 2024.

S. Muthukumar and A. Ahamed, “A novel framework of DDoS attack detection in network using hybrid heuristic deep learning approaches with attention mechanism,” Journal of High Speed Networks, vol. 30, no. 2, pp. 251–277, 2024.

A. Akinwumi, A. Akingbesote, O. Ajayi and F. Aranuwa, “Detection of distributed denial of service (DDoS) attacks using convolutional neural networks,” Nigerian Journal of Technology, vol. 41, no. 6, pp. 1017–1024, 2023.

S. Rameshkumar, R. Ganesan and A. Merline, “Progressive transfer learning-based deep Q network for DDoS defence in WSN,” Computer Systems Science and Engineering, vol. 44, no. 3, pp. 2379–2394, 2023.

M. D. Prasad, P. B. V. Prasanta and C. Amarnath, “Machine Learning DDoS Detection Using Stochastic Gradient Boosting,” International Journal of Computer Sciences and Engineering, vol. 7, no. 4, pp. 157–166, 2019.

I. Sharafaldin, A. H. Lashkari, S. Hakak, and A. A. Ghorbani, “Developing Realistic Distributed Denial of Service (DDoS) Attack Dataset and Taxonomy,” 2019 International Carnahan Conference on Security Technology (ICCST), Oct. 2019.