mlsanityData to 7 Oct 2026

On Diffusion Modeling for Anomaly Detection

arXiv 2305.18593 ↗First posted 29 May 2023cs.LG cs.AIcited by 71

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

Abstract (arXiv)

Known for their impressive performance in generative modeling, diffusion models are attractive candidates for density-based anomaly detection. This paper investigates different variations of diffusion modeling for unsupervised and semi-supervised anomaly detection. In particular, we find that Denoising Diffusion Probability Models (DDPM) are performant on anomaly detection benchmarks yet computationally expensive. By simplifying DDPM in application to anomaly detection, we are naturally led to an alternative approach called Diffusion Time Estimation (DTE). DTE estimates the distribution over diffusion time for a given input and uses the mode or mean of this distribution as the anomaly score. We derive an analytical form for this density and leverage a deep neural network to improve inference efficiency. Through empirical evaluations on the ADBench benchmark, we demonstrate that all diffusion-based anomaly detection methods perform competitively for both semi-supervised and unsupervised settings. Notably, DTE achieves orders of magnitude faster inference time than DDPM, while outperforming it on this benchmark. These results establish diffusion-based anomaly detection as a scalable alternative to traditional methods and recent deep-learning techniques for standard unsupervised and semi-supervised anomaly detection settings.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 19 of its 52 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

19 of 52 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022TabDDPM: Modelling Tabular Data with Diffusion Models30 Sep

Other references · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  9. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  10. 2022Diffusion Models for Medical Anomaly Detectioncited by 231
  11. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  12. 2020Classification-Based Anomaly Detection for General Datacited by 210
6 more
  1. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  2. 2020COPOD: Copula-Based Outlier Detectioncited by 143
  3. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  4. 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
  5. 2021LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networkscited by 42
  6. 2021Challenges for Unsupervised Anomaly Detection in Particle Physicscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 12; 2025: 30; 2026: 27.

71 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
  2. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  3. 2024Out-of-Distribution Detection with a Single Unconditional Diffusion Modelcited by 22
  4. 2025A Survey on Diffusion Models for Anomaly Detectioncited by 13
  5. 2023Anomaly Detection with Variance Stabilized Density Estimationcited by 8
  6. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  7. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  8. 2025Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matchingcited by 8
  9. 2026From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detectioncited by 8
  10. 2025One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detectioncited by 7
  11. 2024Generate and Instantiate What You Prefer: Text-Guided Diffusion for Sequential Recommendationcited by 6
  12. 2024Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakescited by 5
38 more
  1. 2025Is Hyperbolic Space All You Need for Medical Anomaly Detection?cited by 5
  2. 2026MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detectioncited by 5
  3. 2024Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labelscited by 4
  4. 2025Unsupervised Anomaly Detection through Mass Repulsing Optimal Transportcited by 4
  5. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  6. 2025We Need to Rethink Benchmarking in Anomaly Detectioncited by 4
  7. 2025EigenScore: OOD Detection using Covariance in Diffusion Modelscited by 4
  8. 2026TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inferencecited by 4
  9. 2023Contaminated Multivariate Time-Series Anomaly Detection with Spatio-Temporal Graph Conditional Diffusion Modelscited by 3
  10. 2025InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Modelscited by 3
  11. 2025Unsupervised Surrogate Anomaly Detectioncited by 3
  12. 2025Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Datacited by 3
  13. 2025RDDPM: Robust Denoising Diffusion Probabilistic Model for Unsupervised Anomaly Segmentationcited by 3
  14. 2025VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusioncited by 3
  15. 2026ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimescited by 3
  16. 2024Large Generative Graph Modelscited by 2
  17. 2024Anomaly detection using Diffusion-based methodscited by 2
  18. 2025ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detectioncited by 2
  19. 2024Deep Transductive Outlier Detectioncited by 1
  20. 2024ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effectcited by 1
  21. 2025Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Modelscited by 1
  22. 2025MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detectioncited by 1
  23. 2025Diffusion-Based Electrocardiography Noise Quantification via Anomaly Detectioncited by 1
  24. 2025Contextual Learning for Anomaly Detection in Tabular Datacited by 1
  25. 2026CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detectioncited by 1
  26. 2026FoMo X: Modular Explainability Signals for Outlier Detection Foundation Modelscited by 1
  27. 2026Multimodal Industrial Anomaly Detection via Geometric Priorcited by 1
  28. 2026uLEAD-TabPFN: Uncertainty-aware Dependency-based Anomaly Detection with TabPFNcited by 1
  29. 2026Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detectioncited by 1
  30. 2024Fault Detection in Mobile Networks Using Diffusion Modelscited by 0
  31. 2024Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentationcited by 0
  32. 2025Research on Anomaly Detection Methods Based on Diffusion Modelscited by 0
  33. 2025Investigating Mask-aware Prototype Learning for Tabular Anomaly Detectioncited by 0
  34. 2025Polyra Swarms: A Shape-Based Approach to Machine Learningcited by 0
  35. 2025UniOD: A Universal Model for Outlier Detection across Diverse Domainscited by 0
  36. 2025Time-reversed Flow Matching with Worst Transport in High-dimensional Latent Space for Image Anomaly Detectioncited by 0
  37. 2025AnoF-Diff: One-Step Diffusion-Based Anomaly Detection for Forceful Tool Usecited by 0
  38. 2025Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly Detectioncited by 0

50 most cited of 71 All 71 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction
  2. 2024Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
  3. 2023Time Series Anomaly Detection using Diffusion-based Models
  4. 2023Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection
  5. 2025Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models
  6. 2023Exploring Diffusion Models for Unsupervised Video Anomaly Detection
  7. 2025Physics-Informed Diffusion Models for Unsupervised Anomaly Detection in Multivariate Time Series
  8. 2024Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly Detection