mlsanityData to 14 Oct 2026

Anomaly Detection and Generation with Diffusion Models: A Survey

arXiv 2506.09368 ↗First posted 11 Jun 2025cs.LG cs.AIcited by 8

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Anomaly detection (AD) plays a pivotal role across diverse domains, including cybersecurity, finance, healthcare, and industrial manufacturing, by identifying unexpected patterns that deviate from established norms in real-world data. Recent advancements in deep learning, specifically diffusion models (DMs), have sparked significant interest due to their ability to learn complex data distributions and generate high-fidelity samples, offering a robust framework for unsupervised AD. In this survey, we comprehensively review anomaly detection and generation with diffusion models (ADGDM), presenting a tutorial-style analysis of the theoretical foundations and practical implementations and spanning images, videos, time series, tabular, and multimodal data. Crucially, unlike existing surveys that often treat anomaly detection and generation as separate problems, we highlight their inherent synergistic relationship. We reveal how DMs enable a reinforcing cycle where generation techniques directly address the fundamental challenge of anomaly data scarcity, while detection methods provide critical feedback to improve generation fidelity and relevance, advancing both capabilities beyond their individual potential. A detailed taxonomy categorizes ADGDM methods based on anomaly scoring mechanisms, conditioning strategies, and architectural designs, analyzing their strengths and limitations. We final discuss key challenges including scalability and computational efficiency, and outline promising future directions such as efficient architectures, conditioning strategies, and integration with foundation models (e.g., visual-language models and large language models). By synthesizing recent advances and outlining open research questions, this survey aims to guide researchers and practitioners in leveraging DMs for innovative AD solutions across diverse applications.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 181 of its 262 references that are in the map. First posted on arXiv 11 Jun 2025.

Builds on

181 of 262 references.

Closest ancestors · 26

Same direction, newest first

  1. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model3 Sep
  2. 2024AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model4 Aug
  3. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputation25 Jul
  4. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection11 Jun
  5. 2024Balanced Mixed-Type Tabular Data Synthesis with Diffusion Models12 Apr
  6. 2024DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model20 Mar
  7. 2024Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection18 Mar
  8. 2024A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation29 Feb
  9. 2024Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection9 Jan
  10. 2023DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection11 Dec
  11. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model10 Dec
  12. 2023Time Series Anomaly Detection using Diffusion-based Models2 Nov
14 more
  1. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space14 Oct
  2. 2023DDMT: Denoising Diffusion Mask Transformer Models for Multivariate Time Series Anomaly Detection13 Oct
  3. 2023sasdim: self-adaptive noise scaling diffusion model for spatial time series imputation5 Sep
  4. 2023FinDiff: Diffusion Models for Financial Tabular Data Generation4 Sep
  5. 2023Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Models24 Aug
  6. 2023TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Models23 Jul
  7. 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection14 Jul
  8. 2023Neuro-symbolic Empowered Denoising Diffusion Probabilistic Models for Real-time Anomaly Detection in Industry 4.013 Jul
  9. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Values2 Jul
  10. 2023On Diffusion Modeling for Anomaly Detection29 May
  11. 2023Anomaly Detection with Conditioned Denoising Diffusion Models25 May
  12. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis25 Apr
  13. 2023Exploring Diffusion Models for Unsupervised Video Anomaly Detection12 Apr
  14. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection15 Mar

Other references · 155

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  2. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  3. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  4. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  5. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  6. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  9. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  10. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  11. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  12. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
38 more
  1. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  2. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  3. 2019COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysiscited by 318
  4. 2022Perception Prioritized Training of Diffusion Modelscited by 303
  5. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  6. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 276
  7. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  8. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  9. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  10. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  11. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  12. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  13. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 207
  14. 2019Cross-task weakly supervised learning from instructional videoscited by 199
  15. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  16. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  17. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 175
  18. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Datacited by 174
  19. 2021Neural SDEs as Infinite-Dimensional GANscited by 161
  20. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  21. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  22. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 131
  23. 2023CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Samplingcited by 129
  24. 2020Deep Learning for Medical Anomaly Detection -- A Surveycited by 127
  25. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  26. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  27. 2023Collaborative Diffusion for Multi-Modal Face Generation and Editingcited by 116
  28. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  29. 2023VDT: General-purpose Video Diffusion Transformers via Mask Modelingcited by 103
  30. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  31. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  32. 2022Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Modelscited by 97
  33. 2021UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detectioncited by 93
  34. 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 90
  35. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  36. 2023Provable Dynamic Fusion for Low-Quality Multimodal Datacited by 82
  37. 2022VIDM: Video Implicit Diffusion Modelscited by 78
  38. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77

50 most cited of 155 All 155 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospectscited by 2
  2. 2026Diffusion-Guided Semantic Consistency for Multimodal Heterogeneitycited by 2
  3. 2026Collaborative Adaptive Curriculum for Progressive Knowledge Distillationcited by 2
  4. 2025M2S2L: Mamba-based Multi-Scale Spatial-temporal Learning for Video Anomaly Detectioncited by 1
  5. 2026T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognitioncited by 0
  6. 2026PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMscited by 0
  7. 2026Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuningcited by 0
  8. 2026Limitations of Synthetic Data Generation in Specialized Data-Scarce Domainscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on Diffusion Models for Anomaly Detection
  2. 2025Research on Anomaly Detection Methods Based on Diffusion Models
  3. 2024Anomaly detection using Diffusion-based methods
  4. 2026FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction
  5. 2026Masked Diffusion Modeling for Anomaly Detection
  6. 2025CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection
  7. 2024Adversarially Robust Industrial Anomaly Detection Through Diffusion Model
  8. 2025HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection