Abstract
Evaluating the output of Generative Adversarial Networks (GANs) trained on computer network traffic data is difficult. In this paper, we introduced a strategy using fixed low-dimensional UMAP embeddings of network traffic to compare source and synthetic network traffic qualitatively. We found that UMAP embeddings gave a natural way to evaluate the quality of generated data and infer the fitness of the generating model’s hyperparameters. Further, this evaluation matches with quantitative strategies such as GvR. This strategy adds to the toolbox for evaluating generative methods for network traffic and could be generalized to other tabular data sources which are not easily evaluated.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
This dataset was provided by the U.S. Army CCDC, C5ISR Center. For information contact Metin Ahiskali (mahiskali@ieee.com).
References
Cheng, A.: PAC-GAN: packet generation of network traffic using generative adversarial networks. In: 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), pp. 0728–0734 (2019)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Guyon, I., et al. (eds.), Advances in Neural Information Processing Systems, vol. 30, pp. 5767–5777. Curran Associates, Inc. (2017)
Ring, M., Schlor, D., Landes, D., Hotho, A.: Flow-based network traffic generation using generative adversarial networks. CoRR, abs/1810.07795 (2018)
Schoen, A., Blanc, G., Gimenez, P.F., Han, Y., Majorczyk, F., Me, L.: Towards generic quality assessment of synthetic traffic for evaluating intrusion detection systems. In: RESSI 2022 - Rendez-Vous de la Recherche et de l’Enseignement de la Sécurité des Systèmes d’Information, pp. 1–3, Chambon-sur-Lac, France, May 2022
Syal, A.: Automatic network traffic anomaly detection and analysis using supervised machine learning techniques. PhD thesis (2019)
Xu, L., Skoularidou, M., Cuesta-Infante, A., Veeramachaneni, K.: Modeling tabular data using conditional GAN. CoRR, abs/1907.00503 (2019)
Zingo, P., Novocin, A.: Can GAN-generated network traffic be used to train traffic anomaly classifiers? In: 2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), pp. 0540–0545 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zingo, P.A.T., Novocin, A.P. (2023). Qualitative Analysis of Synthetic Computer Network Data Using UMAP. In: Arai, K. (eds) Advances in Information and Communication. FICC 2023. Lecture Notes in Networks and Systems, vol 652. Springer, Cham. https://doi.org/10.1007/978-3-031-28073-3_56
Download citation
DOI: https://doi.org/10.1007/978-3-031-28073-3_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-28072-6
Online ISBN: 978-3-031-28073-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)