pith. sign in

arxiv: 2507.01976 · v2 · submitted 2025-06-23 · 💻 cs.NI · cs.LG

A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning

Nirhoshan Sivaroopan , Kaushitha Silva , Chamara Madarasingha , Thilini Dahanayaka , Guillaume Jourjon , Anura Jayasumana , Kanchana Thilakarathna This is my paper

Pith reviewed 2026-05-19 07:22 UTC · model grok-4.3

classification 💻 cs.NI cs.LG
keywords network traffic synthesissynthetic data generationdeep learningstatistical modelsdata privacynetwork securitymachine learningsurvey
0
0 comments X

The pith

Synthetic network traffic can be generated from statistical models to deep learning methods to overcome real data limitations like scarcity and privacy risks.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This survey reviews methods for creating artificial network traffic that retains the statistical properties of actual captures. It examines traditional statistical techniques along with newer deep learning approaches that have developed rapidly in recent years. The authors supply a structured comparison of these methods, introduce an AI tool that applies the comparison to additional papers, and outline remaining open problems. A reader would care because reliable synthetic data supports safer experimentation, model training, and system testing in networking without exposing sensitive information or depending on scarce real traces.

Core claim

The paper establishes that synthetic network traffic generation offers a practical substitute for real data by preserving essential characteristics while resolving issues of scarcity, privacy, and data purity, and that a full review spanning statistical models, their extensions, deep learning techniques, and commercial tools, together with a comparison framework and supporting AI tool, equips researchers with the means to evaluate and advance these methods systematically.

What carries the argument

The central object is the proposed comparison framework for data types and generation models, which organizes the literature and is realized in an AI tool that applies the same framework to any new network traffic generation paper.

If this is right

  • Researchers gain a ready way to compare generation approaches when choosing a method for a given networking task.
  • Commercial tools receive the same structured evaluation as research prototypes, aiding practical adoption.
  • Highlighted open challenges direct attention toward needed improvements in realism and scalability.
  • The survey positions deep learning methods as a natural extension of statistical baselines for future work.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Widespread use of the comparison framework could encourage more uniform evaluation practices across synthetic traffic studies.
  • The same structured review style might transfer usefully to synthetic data problems in adjacent areas such as wireless sensor networks or cloud traffic.
  • Applying the AI tool to papers published after the survey would provide a direct test of how rapidly the field is changing.

Load-bearing premise

The papers and methods examined in the review represent the broader field without major omissions or selection bias.

What would settle it

Finding several influential papers on network traffic synthesis that were excluded from the review or showing that the AI comparison tool produces inconsistent results across similar papers would indicate the survey is incomplete.

Figures

Figures reproduced from arXiv: 2507.01976 by Anura Jayasumana, Chamara Madarasingha, Guillaume Jourjon, Kanchana Thilakarathna, Kaushitha Silva, Nirhoshan Sivaroopan, Thilini Dahanayaka.

Figure 1
Figure 1. Figure 1: Research papers in network traffic generation [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Different network traffic data types/formats used and data collection points in network traffic generation [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Extraction of payload, packet level, flow level, [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Overall workflow of major statistical methods used. [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Trends in research papers highlighting the focus [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Basic functionality of VAE 1) Vanilla VAE: Kakkavas et al. [66] focuses on gen￾erating synthetic network traffic matrices (TM) to aid in network management and traffic engineering. TM generation is necessary because direct measurements of traffic are costly and difficult to obtain at scale. By using historical data to train a vanilla VAE, the model learns the underlying traffic patterns and generates new t… view at source ↗
Figure 7
Figure 7. Figure 7: Basic functionality of a GAN 1) Vanilla GAN: The basic GAN model, which com￾prises of only generator and discriminator modules, has shown promising results in maintaining network traffic properties, despite the sequential nature they present, in network traffic generation. The authors in [109] focused on creating a protocol-agnostic framework for packet gener￾ation developing a platform named MiragePkt. In… view at source ↗
Figure 8
Figure 8. Figure 8: Basic functionality of DM 1) Denoising Diffusion Probabilistic Model (DDPM): DDPMs optimize the denoising process by explicitly [PITH_FULL_IMAGE:figures/full_fig_p018_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Basic functionality of Transformers 1) Generative Pretrained Transformers (GPT): Gen￾erative Pretrained Transformers (GPT) are a specific class of transformer models initially developed for natural language processing (NLP). Their utility extended beyond NLP, finding applications in various fields, including net- [PITH_FULL_IMAGE:figures/full_fig_p021_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: , this approach can be used to create distinct clusters for each domain, and within each domain, fur￾ther distinct clusters are formed based on content. Once trained, the latent vector for a traffic trace could be extrapolated in the latent space to generate a trace with a different content or domain. For example, [PITH_FULL_IMAGE:figures/full_fig_p028_10.png] view at source ↗
read the original abstract

Synthetic network traffic generation has emerged as a promising alternative for various data-driven applications in the networking domain. It enables the creation of synthetic data that preserves real-world characteristics while addressing key challenges such as data scarcity, privacy concerns, and purity constraints associated with real data. In this survey, we provide a comprehensive review of synthetic network traffic generation approaches, covering essential aspects such as data types and generation models. With the rapid advancements in Artificial Intelligence (AI) and Machine Learning (ML), we focus particularly on deep learning (DL)-based techniques while also providing a detailed discussion of statistical methods and their extensions, including commercially available tools. We present a comprehensive comparision of generation approaches and provide an AI tool to apply this comparision for any network traffic generation papers. Furthermore, we highlight open challenges in this domain and discuss potential future directions for further research and development. This survey serves as a foundational resource for researchers and practitioners, offering a structured analysis of existing methods, challenges, and opportunities in synthetic network traffic generation.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper is a survey on synthetic network traffic generation that reviews statistical models and extensions, deep learning techniques, commercial tools, presents a comparison of approaches, introduces an AI tool for applying comparisons to new papers, and discusses open challenges and future directions.

Significance. If the coverage proves representative, the survey would serve as a useful foundational resource by structuring the progression from statistical to DL-based methods and providing a comparison framework plus AI tool for ongoing use in networking research.

major comments (1)
  1. [Abstract and Introduction] Abstract and Introduction: The manuscript asserts a 'comprehensive review' and coverage of the field but provides no explicit literature search protocol (databases, keywords, date bounds, inclusion criteria). This is load-bearing for the central claim of representativeness without selection bias, as the skeptic note correctly identifies.
minor comments (2)
  1. [Abstract] Abstract: 'comparision' is misspelled (appears twice); correct to 'comparison'.
  2. [Abstract] Abstract: The description of the 'AI tool' is too brief; clarify its implementation, availability, and how it operationalizes the comparison framework.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive feedback on our survey. We address the major comment below and will incorporate revisions to improve transparency.

read point-by-point responses

  1. Referee: [Abstract and Introduction] Abstract and Introduction: The manuscript asserts a 'comprehensive review' and coverage of the field but provides no explicit literature search protocol (databases, keywords, date bounds, inclusion criteria). This is load-bearing for the central claim of representativeness without selection bias, as the skeptic note correctly identifies.

    Authors: We agree that an explicit literature search protocol is important to substantiate the claim of a comprehensive and representative review. The current version of the manuscript does not detail the search methodology. In the revised manuscript, we will add a dedicated subsection (likely in Section 1 or a new Section 2) describing the literature search protocol. This will specify the databases and repositories consulted (IEEE Xplore, ACM Digital Library, Springer Link, arXiv, and Google Scholar), the keywords and search strings employed (e.g., combinations of 'network traffic synthesis', 'synthetic traffic generation', 'deep learning for network traffic', 'GAN traffic generation', 'statistical models for traffic synthesis'), the date range (approximately 2000–2024 with emphasis on post-2015 DL works), and inclusion/exclusion criteria (peer-reviewed journal/conference papers and high-quality preprints focused on statistical or DL-based methods for network traffic generation, excluding purely theoretical works without generation aspects). This addition will enhance transparency and directly address potential concerns about selection bias. revision: yes

Circularity Check

0 steps flagged

No circularity: survey contains no derivations or self-referential predictions

full rationale

This is a literature review paper with no mathematical derivations, fitted parameters, predictions, or load-bearing self-citations that reduce to the paper's own inputs. The central contribution is a structured summary of external methods, statistical models, DL techniques, and an AI comparison tool; these elements draw from cited prior work rather than defining results in terms of themselves. No equations or claims exhibit self-definition, renaming of known results as novel, or uniqueness theorems imported from the authors' prior papers. The absence of a documented search protocol is a methodological limitation but does not constitute circularity under the specified patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a survey paper with no new mathematical derivations, empirical claims, or postulated entities. It relies entirely on summarizing prior literature.

pith-pipeline@v0.9.0 · 5741 in / 1150 out tokens · 33887 ms · 2026-05-19T07:22:15.760250+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

185 extracted references · 185 canonical work pages

  1. [1]

    Synthetic and privacy-preserving traffic trace generation using generative ai models for training network intrusion detection systems,

    G. Aceto, F. Giampaolo, C. Guida, S. Izzo, A. Pescap` e, F. Piccialli, and E. Prezioso, “Synthetic and privacy-preserving traffic trace generation using generative ai models for training network intrusion detection systems,” Journal of Network and Computer Applications, vol. 229, 2024

    work page 2024

  2. [2]

    Network traffic generation: A survey and methodology,

    O. A. Adeleke, N. Bastin, and D. Gurkan, “Network traffic generation: A survey and methodology,” ACM Computing Surveys (CSUR), vol. 55, no. 2, pp. 1–23, 2022

    work page 2022

  3. [3]

    A review of generative models in generating synthetic attack data for cybersecurity,

    G. Agrawal, A. Kaur, and S. Myneni, “A review of generative models in generating synthetic attack data for cybersecurity,” Electronics, vol. 13, no. 2, p. 322, 2024

    work page 2024

  4. [4]

    Network traffic forecasting based on fixed telecommunication data using deep learning,

    M. Alizadeh, M. T. H. Beheshti, A. Ramezani, and H. Saa- datinezhad, “Network traffic forecasting based on fixed telecommunication data using deep learning,” in 6th Iranian Conference on Signal Processing and Intelligent Systems (IC- SPIS), 2020, pp. 1–7

    work page 2020

  5. [5]

    Create a realistic iot dataset using conditional generative adversarial network,

    M. Almasre and A. Subahi, “Create a realistic iot dataset using conditional generative adversarial network,” Journal of Sensor and Actuator Networks, vol. 13, no. 5, p. 62, 2024

    work page 2024

  6. [6]

    Band- width utilization with network traffic analysis,

    N. Alzibdeh, M. T. Alrashdan, and A. Almabhouh, “Band- width utilization with network traffic analysis,” in 3rd Inter- national Conference on Mobile Networks and Wireless Com- munications (ICMNWC). IEEE, 2023, pp. 1–5

    work page 2023

  7. [7]

    A new tool for generating realistic internet traffic in ns-3,

    D. Ammar, T. Begin, and I. Guerin-Lassous, “A new tool for generating realistic internet traffic in ns-3,” in 4th international ICST Conference on Simulation Tools and Techniques, 2012

    work page 2012

  8. [8]

    Generative adversarial networks for network traffic feature generation,

    T. J. Anande, S. Al-Saadi, and M. S. Leeson, “Generative adversarial networks for network traffic feature generation,” International Journal of Computers and Applications, vol. 45, no. 4, pp. 297–305, 2023

    work page 2023

  9. [9]

    Generative adversarial networks (gans): a survey of network traffic generation,

    T. J. Anande and M. S. Leeson, “Generative adversarial networks (gans): a survey of network traffic generation,” Inter- national Journal of Machine Learning and Computing, vol. 12, no. 6, pp. 333–343, 2022

    work page 2022

  10. [10]

    Performance analysis of cloud applications,

    D. Ardelean, A. Diwan, and C. Erdman, “Performance analysis of cloud applications,” in 15th USENIX Symposium on Net- worked Systems Design and Implementation, 2018, pp. 405– 417

    work page 2018

  11. [11]

    The role of the weibull distribution in modelling traffic in internet access and backbone core networks,

    A. Arfeen, K. Pawlikowski, D. McNickle, and A. Willig, “The role of the weibull distribution in modelling traffic in internet access and backbone core networks,” Journal of network and computer applications, vol. 141, pp. 1–22, 2019

    work page 2019

  12. [12]

    The role of the weibull distribution in internet traffic mod- eling,

    M. A. Arfeen, K. Pawlikowski, D. McNickle, and A. Willig, “The role of the weibull distribution in internet traffic mod- eling,” in Proceedings of the 25th International Teletraffic Congress. IEEE, 2013, pp. 1–8

    work page 2013

  13. [13]

    Balancing reconstruction error and kullback-leibler divergence in variational autoencoders,

    A. Asperti and M. Trentin, “Balancing reconstruction error and kullback-leibler divergence in variational autoencoders,” IEEE Access, vol. 8, pp. 199440–199448, 2020

    work page 2020

  14. [14]

    Avoiding traceroute anomalies with paris traceroute,

    B. Augustin, X. Cuvellier, B. Orgogozo, F. Viger, T. Friedman, M. Latapy, C. Magnien, and R. Teixeira, “Avoiding traceroute anomalies with paris traceroute,” in Proceedings of the 6th ACM SIGCOMM Conference on Internet Measurement. As- sociation for Computing Machinery, 2006, p. 153–158

    work page 2006

  15. [15]

    Qos provisioning framework for service-oriented internet of things (iot),

    M. M. Badawy, Z. H. Ali, and H. A. Ali, “Qos provisioning framework for service-oriented internet of things (iot),” Cluster Computing, vol. 23, no. 2, pp. 575–591, 2020

    work page 2020

  16. [16]

    Variational autoencoders for noise resistant traffic generation in b5g networks,

    S. Bano, P. Cassar´ a, and L. Valerio, “Variational autoencoders for noise resistant traffic generation in b5g networks,” in IEEE International Mediterranean Conference on Communications and Networking (MeditCom), 2024, pp. 13–18

    work page 2024

  17. [17]

    Variational auto-encoder: not all failures are equal,

    V. Berger and M. Sebag, “Variational auto-encoder: not all failures are equal,” 2020

    work page 2020

  18. [18]

    Generative trans- former framework for network traffic generation and classifi- cation,

    R. F. Bikmukhamedov and A. F. Nadeev, “Generative trans- former framework for network traffic generation and classifi- cation,” T-Comm-Телекоммуникации и Транспорт, vol. 14, no. 11, pp. 64–71, 2020

    work page 2020

  19. [19]

    Variational inference: A review for statisticians,

    D. M. Blei, A. Kucukelbir, and J. D. McAuliffe, “Variational inference: A review for statisticians,” Journal of the American statistical Association, vol. 112, no. 518, pp. 859–877, 2017

    work page 2017

  20. [20]

    Synthetic data generation for steel defect detection and classification using deep learning,

    A. Boikov, V. Payor, R. Savelev, and A. Kolesnikov, “Synthetic data generation for steel defect detection and classification using deep learning,” Symmetry, vol. 13, no. 7, p. 1176, 2021

    work page 2021

  21. [21]

    A review of tabular data synthesis using gans on an ids dataset,

    S. Bourou, A. El Saer, T.-H. Velivassaki, A. Voulkidis, and T. Zahariadis, “A review of tabular data synthesis using gans on an ids dataset,” Information, vol. 12, no. 09, p. 375, 2021

    work page 2021

  22. [22]

    Benchmarking Methodology for Network Interconnect Devices,

    S. Bradner and J. McQuaid, “Benchmarking Methodology for Network Interconnect Devices,” 1999. [Online]. Available: https://www.rfc-editor.org/info/rfc2544

    work page 1999

  23. [23]

    Generative adversarial networks in time series: A systematic literature review,

    E. Brophy, Z. Wang, Q. She, and T. Ward, “Generative adversarial networks in time series: A systematic literature review,” ACM Computing Surveys, vol. 55, no. 10, pp. 1–31, 2023

    work page 2023

  24. [24]

    Tbi: End-to-end network performance measurement testbed for empirical bottleneck detection

    P. Calyam, D. Krymskiy, M. Sridharan, and P. Schopis, “Tbi: End-to-end network performance measurement testbed for empirical bottleneck detection.” in TRIDENTCOM, 2005, pp. 290–298

    work page 2005

  25. [25]

    Diffusion model-based mobile traffic generation with open data for network planning and optimization,

    H. Chai, T. Jiang, and L. Yu, “Diffusion model-based mobile traffic generation with open data for network planning and optimization,” in Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024, pp. 4828–4838

    work page 2024

  26. [26]

    Knowledge guided conditional diffusion model for controllable mobile traffic generation,

    H. Chai, T. Li, F. Jiang, S. Zhang, and Y. Li, “Knowledge guided conditional diffusion model for controllable mobile traffic generation,” in Companion Proceedings of the ACM on Web Conference, 2024, pp. 851–854

    work page 2024

  27. [27]

    Smote: synthetic minority over-sampling tech- nique,

    N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “Smote: synthetic minority over-sampling tech- nique,” Journal of artificial intelligence research, vol. 16, pp. 321–357, 2002

    work page 2002

  28. [28]

    Par-gan: improving the generalization of generative adversarial networks against membership inference attacks,

    J. Chen, W. H. Wang, H. Gao, and X. Shi, “Par-gan: improving the generalization of generative adversarial networks against membership inference attacks,” in Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 127–137

    work page 2021

  29. [29]

    Synthetic data in machine learning for medicine and healthcare,

    R. J. Chen, M. Y. Lu, T. Y. Chen, D. F. Williamson, and F. Mahmood, “Synthetic data in machine learning for medicine and healthcare,” Nature Biomedical Engineering, vol. 5, no. 6, pp. 493–497, 2021

    work page 2021

  30. [30]

    Pac-gan: Packet generation of network traffic using generative adversarial networks,

    A. Cheng, “Pac-gan: Packet generation of network traffic using generative adversarial networks,” in 2019 IEEE 10th Annual Information Technology, Electronics and Mobile Communica- tion Conference (IEMCON), pp. 0728–0734

    work page 2019

  31. [31]

    Rf-diffusion: Radio signal generation via time-frequency diffusion,

    G. Chi, Z. Yang, C. Wu, J. Xu, Y. Gao, Y. Liu, and T. X. Han, “Rf-diffusion: Radio signal generation via time-frequency diffusion,” in Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. Associa- tion for Computing Machinery, 2024, p. 77–92

    work page 2024

  32. [32]

    Combating imbalance in network intrusion datasets

    D. A. Cieslak, N. V. Chawla, and A. Striegel, “Combating imbalance in network intrusion datasets.” in GrC, 2006, pp. 732–737

    work page 2006

  33. [33]

    TRex – Realistic Traffic Generator,

    CISCO, “TRex – Realistic Traffic Generator,” 2023. [Online]. Available: https://trex-tgn.cisco.com/

    work page 2023

  34. [34]

    [Online]

    Cisco Systems, Inc., Cisco Meraki: Cloud-Managed IT Solutions. [Online]. Available: https://meraki.cisco.com

    work page

  35. [35]

    Citrix Systems, Inc., AppFlow, n.d., https:// docs.netscaler.com/en-us/citrix-adc/current-release/ ns-ag-appflow-intro-wrapper-con.html#:~:text=for% 20each%20transaction.-,Flow%20Records,sent%20before% 20sending%20flow%20records

    work page

  36. [36]

    Challenges in the capture and dissemination of measurements from high-speed networks,

    R. G. Clegg, M. S. Withall, A. W. Moore, I. W. Phillips, D. J. Parish, M. Rio, R. Landa, H. Haddadi, K. Kyriakopoulos, J. Auge et al., “Challenges in the capture and dissemination of measurements from high-speed networks,” IET communica- tions, vol. 3, no. 6, pp. 957–966, 2009

    work page 2009

  37. [37]

    Spirent TestCenter—Verifying Network and Cloud Evolution - Spirent

    S. Communications., “Spirent TestCenter—Verifying Network and Cloud Evolution - Spirent.” 2020. [Online]. Available: https://www.spirent.com/products/testcenter

    work page 2020

  38. [38]

    Tap cassettes,

    F. Community, “Tap cassettes,” 2024. [Online]. Available: https://www.fs.com/au/c/tap-cassettes-1190

    work page 2024

  39. [39]

    A@articleconti2015analyzing,

    M. Conti, L. V. Mancini, R. Spolaor, and N. V. Verde, “A@articleconti2015analyzing,” IEEE Transactions on Infor- mation Forensics and Security, vol. 11, no. 1, pp. 114–125, 2015

    work page 2015

  40. [40]

    On generating network traffic datasets with synthetic attacks for intrusion detection,

    C. G. Cordero, E. Vasilomanolakis, A. Wainakh, M. M¨ uhlh¨ auser, and S. Nadjm-Tehrani, “On generating network traffic datasets with synthetic attacks for intrusion detection,” ACM Transactions on Privacy and Security (TOPS), vol. 24, no. 2, pp. 1–39, 2021. 30

    work page 2021

  41. [41]

    Internet traffic forecasting using neural networks,

    P. Cortez, M. Rio, M. Rocha, and P. Sousa, “Internet traffic forecasting using neural networks,” in IEEE international joint conference on neural network proceedings, 2006, pp. 2635– 2642

    work page 2006

  42. [42]

    A packet generator on the netfpga platform,

    G. A. Covington, G. Gibb, J. W. Lockwood, and N. Mckeown, “A packet generator on the netfpga platform,” in 17th IEEE Symposium on Field Programmable Custom Computing Ma- chines, 2009, pp. 235–238

    work page 2009

  43. [43]

    Internet traffic modeling by means of hidden markov models,

    A. Dainotti, A. Pescap´ e, P. S. Rossi, F. Palmieri, and G. Ven- tre, “Internet traffic modeling by means of hidden markov models,” Computer Networks, vol. 52, no. 14, pp. 2645–2662, 2008

    work page 2008

  44. [44]

    Take a close look at mode collapse and vanishing gradient in gan,

    Z. Ding, S. Jiang, and J. Zhao, “Take a close look at mode collapse and vanishing gradient in gan,” in IEEE 2nd Interna- tional Conference on Electronic Technology, Communication and Information (ICETCI), 2022, pp. 597–602

    work page 2022

  45. [45]

    Pcapgan: Packet capture file generator by style-based generative adversarial networks,

    B. Dowoo, Y. Jung, and C. Choi, “Pcapgan: Packet capture file generator by style-based generative adversarial networks,” in 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), pp. 1149–1154

    work page 2019

  46. [46]

    Network monitoring,

    Dynatrace., “Network monitoring,” 2024. [Online]. Available: https://www.dynatrace.com/monitoring/platform/ network-monitoring/

    work page 2024

  47. [47]

    MoonGen: A Scriptable High-Speed Packet Gen- erator,

    P. Emmerich, S. Gallenm¨ uller, D. Raumer, F. Wohlfart, and G. Carle, “MoonGen: A Scriptable High-Speed Packet Gen- erator,” in Internet Measurement Conference 2015 (IMC’15), 2015

    work page 2015

  48. [48]

    Gan tunnel: Network traffic steganography by using gans to counter internet traffic classifiers,

    S. Fathi-Kazerooni and R. Rojas-Cessa, “Gan tunnel: Network traffic steganography by using gans to counter internet traffic classifiers,” Ieee Access, vol. 8, 2020

    work page 2020

  49. [49]

    Cicflowmeter: Network traffic flow generator,

    C. I. for Cybersecurity, “Cicflowmeter: Network traffic flow generator,” 2017. [Online]. Available: https://www.unb.ca/ cic/research/applications.html

    work page 2017

  50. [50]

    Modelling the network behaviour of malware to block malicious patterns. the stratosphere project: a be- havioural ips,

    S. Garcia, “Modelling the network behaviour of malware to block malicious patterns. the stratosphere project: a be- havioural ips,” Virus Bulletin, pp. 1–8, 2015

    work page 2015

  51. [51]

    A neural algorithm of artistic style,

    L. Gatys, A. Ecker, and M. Bethge, “A neural algorithm of artistic style,” Journal of Vision, vol. 16, no. 12, p. 326, 2016

    work page 2016

  52. [52]

    Generative adversarial nets,

    I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde- Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” Advances in neural information processing systems, vol. 27, 2014

    work page 2014

  53. [53]

    HackRF One: Software Defined Radio,

    Great Scott Gadgets, “HackRF One: Software Defined Radio,” https://greatscottgadgets.com/hackrf/, 2024

    work page 2024

  54. [54]

    Datasets are not enough: Challenges in labeling network traffic,

    J. L. Guerra, C. Catania, and E. Veas, “Datasets are not enough: Challenges in labeling network traffic,” Computers & Security, vol. 120, p. 102810, 2022

    work page 2022

  55. [55]

    Combating imbalance in network traffic classification using ganbasedoversampling,

    Y. Guo, G. Xiong, Z. Li, J. Shi, M. Cui, and G. Gou, “Combating imbalance in network traffic classification using ganbasedoversampling,” in2021IFIPNetworkingConference

    work page

  56. [56]

    Applying generative machine learning to intrusion detection: A systematic mapping study and review,

    J. Halvorsen, C. Izurieta, H. Cai, and A. H. Gebremedhin, “Applying generative machine learning to intrusion detection: A systematic mapping study and review,” ACM Computing Surveys, 2024

    work page 2024

  57. [57]

    A packet-length-adjustable attention model based on bytes embedding using flow-wgan for smart cybersecurity,

    L. Han, Y. Sheng, and X. Zeng, “A packet-length-adjustable attention model based on bytes embedding using flow-wgan for smart cybersecurity,” IEEE Access, vol. 7, pp. 82913–82926, 2019

    work page 2019

  58. [58]

    Gans trained by a two time-scale update rule converge to a local nash equilibrium,

    M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, and S. Hochreiter, “Gans trained by a two time-scale update rule converge to a local nash equilibrium,” Advances in neural information processing systems, vol. 30, 2017

    work page 2017

  59. [59]

    Reducing the dimen- sionality of data with neural networks,

    G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimen- sionality of data with neural networks,” science, vol. 313, no. 5786, pp. 504–507, 2006

    work page 2006

  60. [60]

    Denoisingdiffusionprobabilistic models,

    J.Ho,A.Jain,andP.Abbeel,“Denoisingdiffusionprobabilistic models,” in Advances in Neural Information Processing Sys- tems, vol. 33. Curran Associates, Inc., 2020, pp. 6840–6851

    work page 2020

  61. [61]

    Flow monitoring explained: From packet capture to data analysis with netflow and ipfix,

    R. Hofstede, P. ˇCeleda, B. Trammell, I. Drago, R. Sadre, A. Sperotto, and A. Pras, “Flow monitoring explained: From packet capture to data analysis with netflow and ipfix,” IEEE Communications Surveys & Tutorials, vol. 16, no. 4, pp. 2037– 2064, 2014

    work page 2037

  62. [62]

    Diffupac: Contex- tual mimicry in adversarial packets generation via diffusion model,

    A. B. Jasni, A. Manada, and K. Watabe, “Diffupac: Contex- tual mimicry in adversarial packets generation via diffusion model,” in The Thirty-eighth Annual Conference on Neural Information Processing Systems

    work page

  63. [63]

    Towards synthetic network traffic generating in ntn-enabled iot: A generative ai,

    D. Jiang, Z. Wang, X. Liu, Q. Xu, T. Zou, R. Zhang, L. Tan, and P. Zhang, “Towards synthetic network traffic generating in ntn-enabled iot: A generative ai,” IEEE Internet of Things Journal, 2024

    work page 2024

  64. [64]

    Netdiffusion: Net- work data augmentation through protocol-constrained traffic generation,

    X. Jiang, S. Liu, A. Gember-Jacobson, A. N. Bhagoji, P. Schmitt, F. Bronzino, and N. Feamster, “Netdiffusion: Net- work data augmentation through protocol-constrained traffic generation,” Proceedings of the ACM on Measurement and Analysis of Computing Systems, vol. 8, no. 1, pp. 1–32, 2024

    work page 2024

  65. [65]

    Generative, high-fidelity network traces,

    X.Jiang,S.Liu,A.Gember-Jacobson,P.Schmitt,F.Bronzino, and N. Feamster, “Generative, high-fidelity network traces,” in Proceedings of the 22nd ACM Workshop on Hot Topics in Networks, 2023, pp. 131–138

    work page 2023

  66. [66]

    Future network traffic matrix synthesis and estimation based on deep generative models,

    G. Kakkavas, M. Kalntis, V. Karyotis, and S. Papavassiliou, “Future network traffic matrix synthesis and estimation based on deep generative models,” in International Conference on Computer Communications and Networks (ICCCN). IEEE, 2021, pp. 1–8

    work page 2021

  67. [67]

    Seta++: Real- time scalable encrypted traffic analytics in multi-gbps net- works,

    C. Kattadige, K. N. Choi, A. Wijesinghe, A. Nama, K. Thi- lakarathna, S. Seneviratne, and G. Jourjon, “Seta++: Real- time scalable encrypted traffic analytics in multi-gbps net- works,” IEEE Transactions on Network and Service Manage- ment, vol. 18, no. 3, pp. 3244–3259, 2021

    work page 2021

  68. [68]

    Videotrain: A generative adversarial framework for synthetic video traffic generation,

    C. Kattadige, S. R. Muramudalige, K. N. Choi, G. Jourjon, H. Wang, A. Jayasumana, and K. Thilakarathna, “Videotrain: A generative adversarial framework for synthetic video traffic generation,” in IEEE 22nd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoW- MoM), 2021, pp. 209–218

    work page 2021

  69. [69]

    360norvic: 360-degree video classification from mobile encrypted video traffic,

    C. Kattadige, A. Raman, K. Thilakarathna, A. Lutu, and D. Perino, “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, 2021, pp. 58–65

    work page 2021

  70. [70]

    Secure and efficient ai-sdn-based routing for healthcare- consumer internet of things,

    N. A. Khan, I. U. Din, A. Almogren, A. Altameem, M. Guizani et al., “Secure and efficient ai-sdn-based routing for healthcare- consumer internet of things,” IEEE Transactions on Consumer Electronics, 2024

    work page 2024

  71. [71]

    Pac-gpt: A novel approach to generating synthetic network traffic with gpt-3,

    D. K. Kholgh and P. Kostakos, “Pac-gpt: A novel approach to generating synthetic network traffic with gpt-3,” IEEE Access, 2023

    work page 2023

  72. [72]

    Leveraging synthetic data in object detection on unmanned aerial vehicles,

    B. Kiefer, D. Ott, and A. Zell, “Leveraging synthetic data in object detection on unmanned aerial vehicles,” in 26th inter- national conference on pattern recognition (ICPR). IEEE, 2022, pp. 3564–3571

    work page 2022

  73. [73]

    Network traffic synthesis and simulation framework for cybersecurity exercise systems

    D.-W. Kim, G.-Y. Sin, K. Kim, J. Kang, S.-Y. Im, and M.- M. Han, “Network traffic synthesis and simulation framework for cybersecurity exercise systems.” Computers, Materials & Continua, vol. 80, no. 3, 2024

    work page 2024

  74. [74]

    Enabling automatic protocol behavior analysis for android applications,

    J. Kim, H. Choi, H. Namkung, W. Choi, B. Choi, H. Hong, Y. Kim, J. Lee, and D. Han, “Enabling automatic protocol behavior analysis for android applications,” in Proceedings of the 12th International on Conference on emerging Networking EXperiments and Technologies, 2016, pp. 281–295

    work page 2016

  75. [75]

    Auto-encoding variational bayes,

    D. P. Kingma, M. Welling et al., “Auto-encoding variational bayes,” 2013

    work page 2013

  76. [76]

    Lancet: A self- correcting latency measuring tool,

    M. Kogias, S. Mallon, and E. Bugnion, “Lancet: A self- correcting latency measuring tool,” in USENIX Annual Tech- nical Conference, 2019

    work page 2019

  77. [77]

    High-fidelity cellular network control-plane traffic generation without domain knowledge,

    Z. J. Kong, N. Hu, Y. C. Hu, J. Meng, and Y. Koral, “High-fidelity cellular network control-plane traffic generation without domain knowledge,” in Proceedings of the 2024 ACM on Internet Measurement Conference, 2024, pp. 530–544

    work page 2024

  78. [78]

    KiNETGAN: Enabling Distributed Network Intrusion Detection through Knowledge- Infused Synthetic Data Generation ,

    A. Kotal, B. Luton, and A. Joshi, “ KiNETGAN: Enabling Distributed Network Intrusion Detection through Knowledge- Infused Synthetic Data Generation ,” in 44th International Conference on Distributed Computing Systems Workshops (ICDCSW). IEEE Computer Society, 2024, pp. 140–145

    work page 2024

  79. [79]

    Analysis and modeling of a campus wireless network tcp/ip traffic,

    I. W. Lee and A. O. Fapojuwo, “Analysis and modeling of a campus wireless network tcp/ip traffic,” Computer Networks, vol. 53, no. 15, pp. 2674–2687, 2009

    work page 2009

  80. [80]

    On the self-similar nature of ethernet traffic,

    W. E. Leland, M. S. Taqqu, W. Willinger, and D. V. Wilson, “On the self-similar nature of ethernet traffic,” SIGCOMM Comput. Commun. Rev., vol. 23, no. 4, p. 183–193, 1993

    work page 1993

Showing first 80 references.