mlsanityData to 7 Oct 2026

NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging

arXiv 2310.04429 ↗First posted 23 Sep 2023cs.NI cs.LGcited by 18

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

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.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 23 of its 51 references that are in the map. First posted on arXiv 23 Sep 2023.

Builds on

23 of 51 references.

References · 23

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  5. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  6. 2022Diffusion Models in Vision: A Surveycited by 1,008
  7. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 768
  8. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  9. 2019Modeling Tabular data using Conditional GANcited by 695
  10. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 501
  11. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  12. 2022On the detection of synthetic images generated by diffusion modelscited by 282
11 more
  1. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 161
  2. 2019Classification Accuracy Score for Conditional Generative Modelscited by 134
  3. 2015Imaging Time-Series to Improve Classification and Imputationcited by 85
  4. 2018Deep Fingerprinting: Undermining Website Fingerprinting Defenses with Deep Learningcited by 43
  5. 2020Conditional GAN for timeseries generationcited by 36
  6. 2023Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Modelscited by 20
  7. 2019Machine Learning for Resource Management in Cellular and IoT Networks: Potentials, Current Solutions, and Open Challengescited by 18
  8. 2021A Spectral Enabled GAN for Time Series Data Generationcited by 6
  9. 2021360NorVic: 360-Degree Video Classification from Mobile Encrypted Video Trafficcited by 3
  10. 2023Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectoriescited by 3
  11. 2019Deep-Gap: A deep learning framework for forecasting crowdsourcing supply-demand gap based on imaging time series and residual learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 5.

18 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  2. 2024Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Modelscited by 17
  3. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  4. 2025Mapping the Landscape of Generative AI in Network Monitoring and Managementcited by 4
  5. 2024Data Augmentation for Traffic Classificationcited by 3
  6. 2025Quantifying the Privacy Implications of High-Fidelity Synthetic Network Trafficcited by 3
  7. 2025A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learningcited by 2
  8. 2025Multi-Scale Diffusion Transformer for Jointly Simulating User Mobility and Mobile Traffic Patterncited by 1
  9. 2026A-THENA: Early Intrusion Detection for IoT with Time-Aware Hybrid Encoding and Network-Specific Augmentationcited by 1
  10. 2024SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuingcited by 0
  11. 2025Univariate to Multivariate: LLMs as Zero-Shot Predictors for Time-Series Forecastingcited by 0
  12. 2025LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic Predictioncited by 0
6 more
  1. 2025Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field Diffusioncited by 0
  2. 2025Denoising Refinement Diffusion Models for Simultaneous Generation of Multi-scale Mobile Network Trafficcited by 0
  3. 2026TempoNet: Learning Realistic Communication and Timing Patterns for Network Traffic Simulationcited by 0
  4. 2026Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classificationcited by 0
  5. 2026TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classificationcited by 0
  6. 2026PrivateHub: Contrastive Diffusion Model for Private Sensor-Intensive Environment Data Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models Meet Network Management: Improving Traffic Matrix Analysis with Diffusion-based Approach
  2. 2026Accurate Network Traffic Matrix Prediction via LEAD: a Large Language Model-Enhanced Adapter-Based Conditional Diffusion Model
  3. 2025Multivariate Time Series Anomaly Detection using DiffGAN Model
  4. 2026NetDiffuser: Deceiving DNN-Based Network Attack Detection Systems with Diffusion-Generated Adversarial Traffic
  5. 2025Unveiling the Power of Noise Priors: Enhancing Diffusion Models for Mobile Traffic Prediction
  6. 2023ChatTraffic: Text-to-Traffic Generation via Diffusion Model
  7. 2024BjTT: A Large-scale Multimodal Dataset for Traffic Prediction
  8. 2026NetMamba+: A Framework of Pre-trained Models for Efficient and Accurate Network Traffic Classification