Exploring the Application of Generative Adversarial Networks for Encrypted Traffic Classification in SDN-Enabled Home Networks
Received: 12 July 2025 | Revised: 8 August 2025 | Accepted: 20 August 2025 | Online: 13 September 2025
Corresponding author: Gowthami Chopparapu
Abstract
The rapid growth of encrypted network traffic poses significant challenges for traditional classification methods, particularly in Software-Defined Networking (SDN)-enabled home networks, where direct packet inspection is restricted by privacy requirements. To address this, we propose a Generative Adversarial Network (GAN)-based framework that classifies encrypted traffic using only flow metadata and statistical features, without requiring decryption. The proposed model leverages adversarial learning to capture complex traffic patterns and distinguish between benign and malicious flows, ensuring both high accuracy and privacy preservation. Experimental evaluation on the ISCX VPN dataset demonstrates that our approach outperforms conventional classifiers such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Support Vector Machines (SVMs), and Random Forest, achieving 98.8% accuracy, precision, and recall, an Area Under the Curve (AUC) of 0.995, and a low inference time of 2 ms. Furthermore, the model achieves very low false positive and false negative rates (0.006 for each), highlighting its robustness for real-time applications. This framework provides a scalable, efficient, and privacy-preserving solution for encrypted traffic classification in SDN-enabled home networks, offering a promising direction for secure and intelligent network management.
Keywords:
Generative Adversarial Networks (GANs), encrypted traffic classification, machine learning, cybersecurity, deep learning, network securityDownloads
References
Y. Zion, C. Hajaj, A. Dvir, G. Ben-Artzi, S. Mahpod, and R. Dubin, "Revolutionizing Our Way to Better Classifiers: Leveraging Synthetic Data with Generative Models for Encrypted Network Traffic Classification." Social Science Research Network, Rochester, NY, Dec. 05, 2023.
P. Wang, Z. Wang, F. Ye, and X. Chen, "ByteSGAN: A Semi-supervised Generative Adversarial Network for Encrypted Traffic Classification of SDN Edge Gateway in Green Communication Network." arXiv, Mar. 09, 2021.
Y. Guo, G. Xiong, Z. Li, J. Shi, M. Cui, and G. Gou, "Combating Imbalance in Network Traffic Classification Using GAN Based Oversampling," in 2021 IFIP Networking Conference (IFIP Networking), Espoo and Helsinki, Finland, 2021, pp. 1–9.
G. Han, H. Zhang, Z. Zhang, Y. Ma, and T. Yang, "AI-Based Malicious Encrypted Traffic Detection in 5G Data Collection and Secure Sharing," Electronics, vol. 14, no. 1, Jan. 2025, Art. no. 51.
J. Mao et al., "Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network," Computer Systems Science and Engineering, vol. 39, no. 3, pp. 373–390, Aug. 2021.
P. Wang, S. Li, F. Ye, Z. Wang, and M. Zhang, "PacketCGAN: Exploratory Study of Class Imbalance for Encrypted Traffic Classification Using CGAN," in ICC 2020 - 2020 IEEE International Conference on Communications, Dublin, Ireland, 2020, pp. 1–7.
S. M. Rayavarapu, S. P. Tammineni, S. R. Gottapu, and A. Singam, "A Review of Generative Adversarial Networks for Security Applications," Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, vol. 14, no. 2, pp. 66–70, Jun. 2024.
Y. Duan, L. Wang, D. Liu, B. Deng, and Y. Tian, "Malware Traffic Classification Based on GAN and BP Neural Networks," in Ubiquitous Security: Second International Conference, UbiSec 2022, Zhangjiajie, China, 2022, pp. 144–160.
Z. Tang, J. Wang, B. Yuan, H. Li, J. Zhang, and H. Wang, "Markov-GAN: Markov image enhancement method for malicious encrypted traffic classification," IET Information Security, vol. 16, no. 6, pp. 442–458, Jun. 2022.
H. Sun, C. Peng, Y. Sang, S. Li, Y. Zhang, and Y. Zhu, "Evading Encrypted Traffic Classifiers by Transferable Adversarial Traffic," in Collaborative Computing: Networking, Applications and Worksharing, 18th EAI International Conference, CollaborateCom 2022, Hangzhou, China, 2022, pp. 153–173.
V. K. Jewani et al., "Enhancing Cyber Security Through Generative Adversarial Networks," in Enhancing Security in Public Spaces Through Generative Adversarial Networks (GANs), S. Ponnusamy, J. Antari, P. Bhaladhare, A. Potgantwar, and S. Kalyanaraman, Eds. Hershey, PA, USA: IGI Global Scientific Publishing, 2024, pp. 177–192.
X. Ma, W. Zhu, Y. Jin, and Y. Gao, "A continual encrypted traffic classification algorithm based on WGAN," in Third International Seminar on Artificial Intelligence, Networking, and Information Technology, Shanghai, China, 2022, pp. 460–466.
R. Changala, S. Kayalvili, M. Farooq, L. M. Rao, V. S. Rao, and S. Muthuperumal, "Using Generative Adversarial Networks for Anomaly Detection in Network Traffic: Advancements in AI Cybersecurity," in 2024 International Conference on Data Science and Network Security, Tiptur, India, 2024, pp. 1–6.
Y. Ding, G. Zhu, D. Chen, X. Qin, M. Cao, and Z. Qin, "Adversarial Sample Attack and Defense Method for Encrypted Traffic Data," IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 10, pp. 18024–18039, Oct. 2022.
C. Xu, R. Xia, Y. Xiao, Y. Li, G. Shi, and K.-C. Chen, "Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks," in ICC 2021 - IEEE International Conference on Communications, Montreal, Canada, 2021, pp. 1–6.
X. Wang, W. Wei, X. Yu, D. Zheng, N. Kuma, and L. Liu, "Ensemble Learning-based Traffic Classification with Small-Scale Datasets for Wireless Networks," in IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops, Vancouver, Canada, 2024, pp. 1–6.
M. Mwita, J. Mbelwa, J. Agbinya, and A. E. Sam, "The Effect of Hyperparameter Optimization on the Estimation of Performance Metrics in Network Traffic Prediction using the Gradient Boosting Machine Model," Engineering, Technology & Applied Science Research, vol. 13, no. 3, pp. 10714–10720, Jun. 2023.
V. Ravi and A. S. Poornima, "SecMa: A Novel Multimodal Autoencoder Framework for Encrypted IoT Traffic Analysis and Attack Detection," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 23020–23026, Jun. 2025.
"VPN-nonVPN dataset (ISCXVPN2016)." Canadian Institute for Cybersecurity, UNB. [Online]. Available: https://www.unb.ca/cic/datasets/vpn.html.
Downloads
How to Cite
License
Copyright (c) 2025 Gowthami Chopparapu, S. Kavitha
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.
