Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging (2310.04429v1)

Published 23 Sep 2023 in cs.NI and cs.LG

Abstract: Network data analytics are now at the core of almost every networking solution. Nonetheless, limited access to networking data has been an enduring challenge due to many reasons including complexity of modern networks, commercial sensitivity, privacy and regulatory constraints. In this work, we explore how to leverage recent advancements in Diffusion Models (DM) to generate synthetic network traffic data. We develop an end-to-end framework - NetDiffus that first converts one-dimensional time-series network traffic into two-dimensional images, and then synthesizes representative images for the original data. We demonstrate that NetDiffus outperforms the state-of-the-art traffic generation methods based on Generative Adversarial Networks (GANs) by providing 66.4% increase in fidelity of the generated data and 18.1% increase in downstream machine learning tasks. We evaluate NetDiffus on seven diverse traffic traces and show that utilizing synthetic data significantly improves traffic fingerprinting, anomaly detection and traffic classification.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Alexa. [n. d.]. Amazon alexa. https://alexa.amazon.com/
  2. Align your latents: High-resolution video synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 22563–22575.
  3. Inferring streaming video quality from encrypted traffic: Practical models and deployment experience. Proceedings of the ACM on Measurement and Analysis of Computing Systems 3, 3 (2019), 1–25.
  4. Adriel Cheng. 2019. PAC-GAN: Packet generation of network traffic using generative adversarial networks. In 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON). IEEE, 0728–0734.
  5. Min Jin Chong and David Forsyth. 2020. Effectively unbiased fid and inception score and where to find them. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 6070–6079.
  6. On the detection of synthetic images generated by diffusion models. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1–5.
  7. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023).
  8. Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems 34 (2021), 8780–8794.
  9. Measuring video QoE from encrypted traffic. In Proceedings of the 2016 Internet Measurement Conference. 513–526.
  10. Real-valued (medical) time series generation with recurrent conditional gans. arXiv preprint arXiv:1706.02633 (2017).
  11. Coarse-graining time series data: Recurrence plot of recurrence plots and its application for music. Chaos: An Interdisciplinary Journal of Nonlinear Science 26, 2 (2016), 023116.
  12. Gramian angular fields for leveraging pretrained computer vision models with anomalous diffusion trajectories. Physical Review E 107, 3 (2023), 034138.
  13. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.
  14. Google. [n. d.]. Compare smart displays. https://store.google.com/au/magazine/compare_nest_hub?hl=en-GB
  15. Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Models. arXiv preprint arXiv:2303.00608 (2023).
  16. Machine learning for resource management in cellular and IoT networks: Potentials, current solutions, and open challenges. IEEE Communications Surveys & Tutorials 22, 2 (2020), 1251–1275.
  17. Iperf.fr. 2023. iPerf - The ultimate speed test tool for TCP, UDP and SCTP. https://iperf.fr/. [Online; accessed 19-June-2023].
  18. VideoTrain: A generative adversarial framework for synthetic video traffic generation. In 2021 IEEE 22nd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM). IEEE, 209–218.
  19. 360NorVic: 360-degree video classification from mobile encrypted video traffic. In Proceedings of the 31st ACM Workshop on Network and Operating Systems Support for Digital Audio and Video. 58–65.
  20. Using GANs for sharing networked time series data: Challenges, initial promise, and open questions. In Proceedings of the ACM Internet Measurement Conference. 464–483.
  21. NS3. 2023. NS-3 Network Simulator. https://www.nsnam.org/. [Online; accessed 19-June-2023].
  22. OpenAI. 2023. DALL-E@. https://openai.com/dall-e-2. [Online; accessed 19-June-2023].
  23. OpenCV. 2023. Geometric Image Transformations. https://docs.opencv.org/3.4/da/d54/group__imgproc__transform.html. [Online; accessed 19-June-2023].
  24. Suman Ravuri and Oriol Vinyals. 2019. Classification accuracy score for conditional generative models. Advances in neural information processing systems 32 (2019).
  25. IP Traffic Generator Based on Hidden Markov Models. parameters 1, 2 ([n. d.]), 1.
  26. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10684–10695.
  27. Ahmed Ben Said and Abdelkarim Erradi. 2019. Deep-Gap: A deep learning framework for forecasting crowdsourcing supply-demand gap based on imaging time series and residual learning. In 2019 IEEE International Conference on Cloud Computing Technology and Science (CloudCom). IEEE, 279–286.
  28. Safe latent diffusion: Mitigating inappropriate degeneration in diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 22522–22531.
  29. Evidential deep learning to quantify classification uncertainty. Advances in neural information processing systems 31 (2018).
  30. Generative deep learning for Internet of Things network traffic generation. In 2020 IEEE 25th Pacific Rim International Symposium on Dependable Computing (PRDC). IEEE, 70–79.
  31. Epileptic seizure classification based on Gramian angular field transformation and deep learning. In 2020 IEEE Applied Signal Processing Conference (ASPCON). IEEE, 147–151.
  32. Deep fingerprinting: Undermining website fingerprinting defenses with deep learning. In Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. 1928–1943.
  33. Kaleb E Smith and Anthony O Smith. 2020. Conditional GAN for timeseries generation. arXiv preprint arXiv:2006.16477 (2020).
  34. Kaleb E Smith and Anthony O Smith. 2021. A spectral enabled gan for time series data generation. arXiv preprint arXiv:2103.01904 (2021).
  35. Yang Song and Stefano Ermon. 2020. Improved techniques for training score-based generative models. Advances in neural information processing systems 33 (2020), 12438–12448.
  36. A Novel Arrhythmia Classification Method Based on GASF and Optimized Inception-Resnet-v2. Available at SSRN 4176688 ([n. d.]).
  37. Zhiguang Wang and Tim Oates. 2015. Imaging time-series to improve classification and imputation.
  38. Modeling tabular data using conditional gan. Advances in Neural Information Processing Systems 32 (2019).
  39. Stan: Synthetic network traffic generation using autoregressive neural models. In arXiv preprint arXiv:2009.12740.
  40. Practical gan-based synthetic ip header trace generation using netshare. In Proceedings of the ACM SIGCOMM 2022 Conference. 458–472.
  41. Time-series generative adversarial networks. Advances in neural information processing systems 32 (2019).
  42. Motiondiffuse: Text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022).
Citations (10)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now