mlsanityData to 7 Oct 2026

Masked Diffusion Modeling for Anomaly Detection

arXiv 2605.30046 ↗First posted 28 May 2026cs.LG cs.AIcited by 0

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

Abstract (arXiv)

Anomaly detection aims to identify samples that deviate from the nominal data distribution and is central to many safety-critical applications. However, developing effective anomaly detection methods for categorical, mixed-type, and discrete sequence data remains challenging and relatively underexplored. Masked diffusion models provide a natural way to model such data by learning to recover masked values from the remaining visible context. In this paper, we propose Masked Diffusion for Anomaly Detection (MaskDiff-AD), a forward-only method based on masked diffusion models trained only on nominal data. Given a test sample, MaskDiff-AD constructs anomaly scores from the difficulty of reconstructing randomly masked coordinates, yielding a content-sensitive score that operates directly on discrete state spaces while avoiding reverse-time sampling. We also develop a non-parametric variant of MaskDiff-AD and provide theoretical guarantees by characterizing Type-I and Type-II errors under a fixed detection threshold. Experiments on fourteen categorical and mixed-type tabular datasets from ADBench and UADAD, as well as four text anomaly detection datasets from NLP-ADBench, show that MaskDiff-AD achieves competitive performance against classical, diffusion-based, and recent tabular/text anomaly detection baselines. Notably, MaskDiff-AD achieves the best overall average rank, outperforming all twelve tabular baseline methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 29 of its 54 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

29 of 54 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025A Survey on Diffusion Models for Anomaly Detection20 Jan
  2. 2023On Diffusion Modeling for Anomaly Detection29 May
  3. 2023Anomaly Detection with Conditioned Denoising Diffusion Models25 May
  4. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection15 Mar

Other references · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  5. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  6. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  7. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  8. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  9. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  10. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  11. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  12. 2020Classification-Based Anomaly Detection for General Datacited by 210
13 more
  1. 2024Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Samplingcited by 204
  2. 2022ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functionscited by 153
  3. 2020COPOD: Copula-Based Outlier Detectioncited by 143
  4. 2024Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Reviewcited by 92
  5. 2018Generative Adversarial Active Learning for Unsupervised Outlier Detectioncited by 65
  6. 2025Diffusion Beats Autoregressive in Data-Constrained Settingscited by 61
  7. 2021DATE: Detecting Anomalies in Text via Self-Supervision of Transformerscited by 25
  8. 2024NLP-ADBench: NLP Anomaly Detection Benchmarkcited by 17
  9. 2021Challenges for Unsupervised Anomaly Detection in Particle Physicscited by 16
  10. 2025Constrained Discrete Diffusioncited by 16
  11. 2023Beyond Individual Input for Deep Anomaly Detection on Tabular Datacited by 14
  12. 2023Few-shot Anomaly Detection in Text with Deviation Learningcited by 11
  13. 2022Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodingscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Research on Anomaly Detection Methods Based on Diffusion Models
  2. 2025Anomaly Detection and Generation with Diffusion Models: A Survey
  3. 2024Anomaly detection using Diffusion-based methods
  4. 2026FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction
  5. 2024Binary Noise for Binary Tasks: Masked Bernoulli Diffusion for Unsupervised Anomaly Detection
  6. 2024Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection
  7. 2025Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
  8. 2024DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector