Design of an Improved Model for DDoS Mitigation in SDN-IoT Using TGNN, QAOA, and the Federated Adversarial Learning Process
Received: 22 May 2025 | Revised: 18 July 2025, 13 August 2025, and 9 September 2025 | Accepted: 13 September 2025 | Online: 8 December 2025
Corresponding author: B. Jyothsna
Abstract
The rapid growth of IoT devices and the dynamic nature of Software Defined Networks (SDNs) present significant challenges for traditional Distributed Denial of Service (DDoS) detection systems. Existing methods often rely on static thresholds and centralized models, limiting their adaptability and effectiveness, especially against stealthy or low-rate DDoS attacks. To address these limitations, this paper presents a novel hybrid framework that integrates temporal learning, quantum-inspired optimization, and federated adversarial training. The system begins with advanced data preprocessing to extract both packet-level and flow-level features. An adaptive reinforcement learning filter dynamically adjusts detection thresholds, reducing false alarms and latency. Temporal and structural correlations across network flows are captured using a temporal graph neural network with time-aware attention mechanisms. Quantum-geometric embedding maps high-dimensional network flow features into a lower-dimensional space using quantum-inspired geometric principles, preserving relational structure for more efficient and scalable analysis. Quantum-geometric embedding techniques compress high-dimensional flow data while preserving structural integrity and improving scalability. Furthermore, a quantum-inspired feature selection algorithm optimizes the feature set for efficient processing. Finally, federated adversarial learning combines local model training with adversarial robustness enhancements to build a secure, decentralized detection system. Experimental evaluations demonstrate a detection accuracy of 97.2%, a 22% improvement in detecting stealth attacks, and a 28% enhancement in adversarial robustness, making this framework highly suitable for modern SDN-IoT ecosystems.
Keywords:
DDoS mitigation, temporal graph neural network, federated learning, quantum optimization, SDN IoT SecurityDownloads
References
W. Hill et al., ''DDoS in SDN: a review of open datasets, attack vectors and mitigation strategies,'' Discover Applied Sciences, vol. 6, no. 9, Aug. 2024, Art. no. 472. DOI: https://doi.org/10.1007/s42452-024-06172-x
A. K. Jain, H. Shukla, and D. Goel, ''A comprehensive survey on DDoS detection, mitigation, and defense strategies in software-defined networks,'' Cluster Computing, vol. 27, no. 9, pp. 13129–13164, Dec. 2024. DOI: https://doi.org/10.1007/s10586-024-04596-z
U. B. Clinton, N. Hoque, and K. R. Singh, ''Classification of DDoS attack traffic on SDN network environment using deep learning,'' Cybersecurity, vol. 7, no. 1, Aug. 2024, Art. no. 23. DOI: https://doi.org/10.1186/s42400-024-00219-7
A. Singh, H. Kaur, and N. Kaur, ''A novel DDoS detection and mitigation technique using hybrid machine learning model and redirect illegitimate traffic in SDN network,'' Cluster Computing, vol. 27, no. 3, pp. 3537–3557, June 2024. DOI: https://doi.org/10.1007/s10586-023-04152-1
A. S. Zaidoun and Z. Lachiri, ''A hybrid deep learning model for multi-class DDoS detection in SDN networks,'' Annals of Telecommunications, vol. 80, no. 5–6, pp. 459–472, June 2025. DOI: https://doi.org/10.1007/s12243-025-01085-1
M. Revathi and S. K. Devi, ''Hybrid architecture for mitigating DDoS and other intrusions in SDN-IoT using MHDBN-W deep learning model,'' International Journal of Machine Learning and Cybernetics, May 2024. DOI: https://doi.org/10.1007/s13042-024-02147-x
B. T. Alemu, A. J. Muhammed, H. M. Belachew, and M. Y. Beyene, ''A comprehensive detection and mitigation mechanism to protect SD-IoV systems against controller-targeted DDoS attacks,'' Cluster Computing, vol. 27, no. 10, pp. 14295–14313, Dec. 2024. DOI: https://doi.org/10.1007/s10586-024-04660-8
G. S. Vidhya and R. Nagarajan, ''A novel bidirectional LSTM model for network intrusion detection in SDN-IoT network,'' Computing, vol. 106, no. 8, pp. 2613–2642, Aug. 2024. DOI: https://doi.org/10.1007/s00607-024-01295-w
D. Mahesh and S. K. Tallapally, ''Advanced SDN-based network security: an ensemble optimized deep learning-based framework for mitigating DDoS attacks with intrusion detection,'' Cluster Computing, vol. 28, no. 5, Aug. 2025, Art. no. 331. DOI: https://doi.org/10.1007/s10586-024-04989-0
T. Linhares, A. Patel, A. L. Barros, and M. Fernandez, ''SDNTruth: Innovative DDoS Detection Scheme for Software-Defined Networks (SDN),'' Journal of Network and Systems Management, vol. 31, no. 3, July 2023, Art. no. 55. DOI: https://doi.org/10.1007/s10922-023-09741-4
B. Swathi, S. S. Kolisetty, G. V. Sivanarayana, and S. R. Battula, ''Efficientnetv2-RegNet: an effective deep learning framework for secure SDN based IOT network,'' Cluster Computing, vol. 27, no. 8, pp. 10653–10670, Nov. 2024. DOI: https://doi.org/10.1007/s10586-024-04498-0
M. Maddu and Y. N. Rao, ''Network intrusion detection and mitigation in SDN using deep learning models,'' International Journal of Information Security, vol. 23, no. 2, pp. 849–862, Apr. 2024. DOI: https://doi.org/10.1007/s10207-023-00771-2
A. Jawahar et al., ''DDoS mitigation using blockchain and machine learning techniques,'' Multimedia Tools and Applications, vol. 83, no. 21, pp. 60265–60278, Jan. 2024. DOI: https://doi.org/10.1007/s11042-023-18028-4
C. R. Babu et al., ''Hybridization of synergistic swarm and differential evolution with graph convolutional network for distributed denial of service detection and mitigation in IoT environment,'' Scientific Reports, vol. 14, no. 1, Dec. 2024, Art. no. 30868. DOI: https://doi.org/10.1038/s41598-024-81116-4
N. Gavric, G. P. Bhandari, and A. Shalaginov, ''Towards Resource-Efficient DDoS Detection in IoT: Leveraging Feature Engineering of System and Network Usage Metrics,'' Journal of Network and Systems Management, vol. 32, no. 4, Oct. 2024, Art. no. 69. DOI: https://doi.org/10.1007/s10922-024-09848-2
A. Sanmorino, L. Marnisah, and H. D. Kesuma, ''Detection of DDoS Attacks using Fine-Tuned Multi-Layer Perceptron Models,'' Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16444–16449, Oct. 2024, https://doi.org/10.48084/etasr.8362. DOI: https://doi.org/10.48084/etasr.8362
G. Sripriyanka and A. Mahendran, ''Smart Healthcare Applications: Detecting DDoS Attacks Efficiently using Hybrid Firefly Algorithm,'' Engineering, Technology & Applied Science Research, vol. 15, no. 2, pp. 21136–21143, Apr. 2025. DOI: https://doi.org/10.48084/etasr.9760
P. D. Bojovic, I. Basicevic, S. Očovaj, and M. Popovic, "DDoS attack scoreboard dataset," vol. 2, Aug. 2017, https://doi.org/10.17632/psjxnzsxyx.2.
"IoT-SDN IDS Dataset." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/hebadhirar/iot-sdn-ids-dataset.
"Edge-IIoTset Cyber Security Dataset of IoT & IIoT." Kaggle, [Online]. https://www.kaggle.com/datasets/mohamedamineferrag/edgeiiotset-cyber-security-dataset-of-iot-iiot.
Downloads
How to Cite
License
Copyright (c) 2025 B. Jyothsna, V. Jyothsna
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
