mlsanityData to 7 Oct 2026

A Survey on Diffusion Models for Anomaly Detection

arXiv 2501.11430 ↗First posted 20 Jan 2025cs.LG cs.AIcited by 13

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

Abstract (arXiv)

Diffusion models (DMs) have emerged as a powerful class of generative AI models, showing remarkable potential in anomaly detection (AD) tasks across various domains, such as cybersecurity, fraud detection, healthcare, and manufacturing. The intersection of these two fields, termed diffusion models for anomaly detection (DMAD), offers promising solutions for identifying deviations in increasingly complex and high-dimensional data. In this survey, we review recent advances in DMAD research. We begin by presenting the fundamental concepts of AD and DMs, followed by a comprehensive analysis of classic DM architectures including DDPMs, DDIMs, and Score SDEs. We further categorize existing DMAD methods into reconstruction-based, density-based, and hybrid approaches, providing detailed examinations of their methodological innovations. We also explore the diverse tasks across different data modalities, encompassing image, time series, video, and multimodal data analysis. Furthermore, we discuss critical challenges and emerging research directions, including computational efficiency, model interpretability, robustness enhancement, edge-cloud collaboration, and integration with large language models. The collection of DMAD research papers and resources is available at https://github.com/fdjingliu/DMAD.

Key facts. Cited by 13 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 37 of its 65 references that are in the map. First posted on arXiv 20 Jan 2025.

Builds on

37 of 65 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model3 Sep
  2. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputation25 Jul
  3. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Data29 Apr
  4. 2024Unsupervised Anomaly Detection via Masked Diffusion Posterior Sampling27 Apr
  5. 2024Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection9 Jan
  6. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model10 Dec
  7. 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection14 Jul
  8. 2023Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations4 Jul
  9. 2023On Diffusion Modeling for Anomaly Detection29 May
  10. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis25 Apr
  11. 2023Exploring Diffusion Models for Unsupervised Video Anomaly Detection12 Apr
  12. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection15 Mar

Other references · 25

  1. 2022Perception Prioritized Training of Diffusion Modelscited by 301
  2. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  3. 2023Diffusion Recommender Modelcited by 87
  4. 2023Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Modelscited by 59
  5. 2023Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Modelscited by 48
  6. 2023A Comprehensive Survey on Knowledge Distillation of Diffusion Modelscited by 45
  7. 2020Perfect density models cannot guarantee anomaly detectioncited by 39
  8. 2023Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Imagescited by 30
  9. 2023Unsupervised Anomaly Detection in Medical Images Using Masked Diffusion Modelcited by 25
  10. 2023Unsupervised 3D out-of-distribution detection with latent diffusion modelscited by 22
  11. 2024AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusioncited by 21
  12. 2024Networking Systems for Video Anomaly Detection: A Tutorial and Surveycited by 21
13 more
  1. 2023Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approachcited by 17
  2. 2023DIFFender: Diffusion-Based Adversarial Defense against Patch Attackscited by 15
  3. 2023The Hidden Linear Structure in Score-Based Models and its Applicationcited by 15
  4. 2023Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equationcited by 12
  5. 2024Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detectioncited by 12
  6. 2024Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Modelscited by 11
  7. 2023Maat: Performance Metric Anomaly Anticipation for Cloud Services with Conditional Diffusioncited by 8
  8. 2023Elucidating the solution space of extended reverse-time SDE for diffusion modelscited by 7
  9. 2023Masked Diffusion with Task-awareness for Procedure Planning in Instructional Videoscited by 7
  10. 2024Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimizationcited by 7
  11. 2023A High-Quality Robust Diffusion Framework for Corrupted Datasetcited by 6
  12. 2024Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioningcited by 2
  13. 2024Statistical Test for Diffusion-Based Anomaly Localization via Selective Inferencecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

  1. 2025Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Artcited by 13
  2. 2025Mobi-π: Mobilizing Your Robot Learning Policycited by 9
  3. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  4. 2025Is Hyperbolic Space All You Need for Medical Anomaly Detection?cited by 5
  5. 2025DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusioncited by 4
  6. 2026Diffusion-Guided Semantic Consistency for Multimodal Heterogeneitycited by 2
  7. 2026Collaborative Adaptive Curriculum for Progressive Knowledge Distillationcited by 2
  8. 2025UniOD: A Universal Model for Outlier Detection across Diverse Domainscited by 0
  9. 2025A Laplace diffusion-based transformer model for heart rate forecasting within daily activity contextcited by 0
  10. 2026Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomaliescited by 0
  11. 2026Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detectioncited by 0
  12. 2026Masked Diffusion Modeling for Anomaly Detectioncited by 0
1 more
  1. 2026Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Anomaly Detection and Generation with Diffusion Models: A Survey
  2. 2025Research on Anomaly Detection Methods Based on Diffusion Models
  3. 2024Anomaly detection using Diffusion-based methods
  4. 2025HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection
  5. 2023Time Series Anomaly Detection using Diffusion-based Models
  6. 2026FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction
  7. 2025Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models
  8. 2025One-for-More: Continual Diffusion Model for Anomaly Detection