Academic Journal
NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation
| العنوان: | NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation |
|---|---|
| المؤلفون: | Jiang, Xi, I, Liu, Shinan, Gember-Jacobson, Aaron, Bhagoji, Arjun Nitin, Schmitt, Paul, Bronzino, Francesco, Feamster, Nick |
| المساهمون: | University of Chicago, Colgate University, University of Hawaii, Holistic Wireless Networks (hownet), Laboratoire de l'Informatique du Parallélisme (LIP), École normale supérieure de Lyon (ENS de Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure de Lyon (ENS de Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Fédération Informatique de Lyon through the INTERFERE project, ANR-21-CE94-0001,MINT,Modélisation du trafic réseau moderne: de la représentation des données à l'apprentissage automatique automatisé(2021) |
| المصدر: | EISSN: 2476-1249 ; Proceedings of the ACM on Measurement and Analysis of Computing Systems ; https://hal.science/hal-04472679 ; Proceedings of the ACM on Measurement and Analysis of Computing Systems , 2024, 8 (1), pp.1-32. ⟨10.1145/3639037⟩ |
| بيانات النشر: | HAL CCSD ACM |
| سنة النشر: | 2024 |
| المجموعة: | HAL Lyon 1 (University Claude Bernard Lyon 1) |
| مصطلحات موضوعية: | Network traffic synthesis diffusion model, Network traffic, synthesis, diffusion model, [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] |
| الوصف: | International audience ; Datasets of labeled network traces are essential for a multitude of machine learning (ML) tasks in networking, yet their availability is hindered by privacy and maintenance concerns, such as data staleness. To overcome this limitation, synthetic network traces can often augment existing datasets. Unfortunately, current synthetic trace generation methods, which typically produce only aggregated flow statistics or a few selected packet attributes, do not always suffice, especially when model training relies on having features that are only available from packet traces. This shortfall manifests in both insufficient statistical resemblance to real traces and suboptimal performance on ML tasks when employed for data augmentation. In this paper, we apply diffusion models to generate high-resolution synthetic network traffic traces. We present NetDiffusion1, a tool that uses a finely-tuned, controlled variant of a Stable Diffusion model to generate synthetic network traffic that is high fidelity and conforms to protocol specifications. Our evaluation demonstrates that packet captures generated from NetDiffusion can achieve higher statistical similarity to real data and improved ML model performance than current state-of-the-art approaches (e.g., GAN-based approaches). Furthermore, our synthetic traces are compatible with common network analysis tools and support a myriad of network tasks, suggesting that NetDiffusion can serve a broader spectrum of network analysis and testing tasks, extending beyond ML-centric applications. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| Relation: | info:eu-repo/semantics/altIdentifier/arxiv/2310.08543; hal-04472679; https://hal.science/hal-04472679; https://hal.science/hal-04472679/document; https://hal.science/hal-04472679/file/2310.08543.pdf; ARXIV: 2310.08543 |
| DOI: | 10.1145/3639037 |
| الاتاحة: | https://hal.science/hal-04472679 https://hal.science/hal-04472679/document https://hal.science/hal-04472679/file/2310.08543.pdf https://doi.org/10.1145/3639037 |
| Rights: | info:eu-repo/semantics/OpenAccess |
| رقم الانضمام: | edsbas.3F45AE7A |
| قاعدة البيانات: | BASE |
| DOI: | 10.1145/3639037 |
|---|