# A Survey on Diffusion Models for Anomaly Detection

arXiv: https://arxiv.org/abs/2501.11430 · HTML: https://mlsanity.com/paper/2501.11430/

## Key facts

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

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 37)

- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model](https://mlsanity.com/paper/2312.05767/) (2023)
- [Diffusion Recommender Model](https://mlsanity.com/paper/2304.04971/) (2023)
- [CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis](https://mlsanity.com/paper/2304.12654/) (2023)
- [On Diffusion Modeling for Anomaly Detection](https://mlsanity.com/paper/2305.18593/) (2023)
- [A Survey on Diffusion Models for Time Series and Spatio-Temporal Data](https://mlsanity.com/paper/2404.18886/) (2024)
- [Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models](https://mlsanity.com/paper/2302.05087/) (2023)
- [Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models](https://mlsanity.com/paper/2305.19643/) (2023)
- [DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection](https://mlsanity.com/paper/2303.08730/) (2023)
- [A Comprehensive Survey on Knowledge Distillation of Diffusion Models](https://mlsanity.com/paper/2304.04262/) (2023)
- [Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection](https://mlsanity.com/paper/2307.07205/) (2023)
- [Perfect density models cannot guarantee anomaly detection](https://mlsanity.com/paper/2012.03808/) (2020)
- [TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model](https://mlsanity.com/paper/2409.02322/) (2024)
- [Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images](https://mlsanity.com/paper/2308.02062/) (2023)
- [Unsupervised Anomaly Detection in Medical Images Using Masked Diffusion Model](https://mlsanity.com/paper/2305.19867/) (2023)
- [Exploring Diffusion Models for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2304.05841/) (2023)
- [Unsupervised 3D out-of-distribution detection with latent diffusion models](https://mlsanity.com/paper/2307.03777/) (2023)
- [AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion](https://mlsanity.com/paper/2404.19444/) (2024)
- [Networking Systems for Video Anomaly Detection: A Tutorial and Survey](https://mlsanity.com/paper/2405.10347/) (2024)
- [Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations](https://mlsanity.com/paper/2307.01533/) (2023)
- [Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach](https://mlsanity.com/paper/2310.18677/) (2023)
- [Self-Supervision Improves Diffusion Models for Tabular Data Imputation](https://mlsanity.com/paper/2407.18013/) (2024)
- [DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks](https://mlsanity.com/paper/2306.09124/) (2023)
- [The Hidden Linear Structure in Score-Based Models and its Application](https://mlsanity.com/paper/2311.10892/) (2023)
- [Closing the ODE-SDE gap in score-based diffusion models through the Fokker-Planck equation](https://mlsanity.com/paper/2311.15996/) (2023)
- [Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2407.06635/) (2024)
- [Hybrid SD: Edge-Cloud Collaborative Inference for Stable Diffusion Models](https://mlsanity.com/paper/2408.06646/) (2024)
- [Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection](https://mlsanity.com/paper/2401.04463/) (2024)
- [Maat: Performance Metric Anomaly Anticipation for Cloud Services with Conditional Diffusion](https://mlsanity.com/paper/2308.07676/) (2023)

## Built on by (most cited first, 13 of 13)

- [Generative Diffusion Models for Wireless Networks: Fundamental, Architecture, and State-of-the-Art](https://mlsanity.com/paper/2507.16733/) (2025)
- [Mobi-π: Mobilizing Your Robot Learning Policy](https://mlsanity.com/paper/2505.23692/) (2025)
- [Foundation Models and Transformers for Anomaly Detection: A Survey](https://mlsanity.com/paper/2507.15905/) (2025)
- [DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion](https://mlsanity.com/paper/2503.06748/) (2025)
- [Is Hyperbolic Space All You Need for Medical Anomaly Detection?](https://mlsanity.com/paper/2505.21228/) (2025)
- [Diffusion-Guided Semantic Consistency for Multimodal Heterogeneity](https://mlsanity.com/paper/2603.19337/) (2026)
- [Collaborative Adaptive Curriculum for Progressive Knowledge Distillation](https://mlsanity.com/paper/2603.20296/) (2026)
- [UniOD: A Universal Model for Outlier Detection across Diverse Domains](https://mlsanity.com/paper/2507.06624/) (2025)
- [A Laplace diffusion-based transformer model for heart rate forecasting within daily activity context](https://mlsanity.com/paper/2508.16655/) (2025)
- [Toxicity Assessment in Preclinical Histopathology via Class-Aware Mahalanobis Distance for Known and Novel Anomalies](https://mlsanity.com/paper/2602.02124/) (2026)
- [Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection](https://mlsanity.com/paper/2603.23766/) (2026)
- [Masked Diffusion Modeling for Anomaly Detection](https://mlsanity.com/paper/2605.30046/) (2026)
- [Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning](https://mlsanity.com/paper/2607.12112/) (2026)

## 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.