A Survey on Diffusion Models for Anomaly Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913709455048704 |
|---|---|
| author | Liu, Jing Ma, Zhenchao Wang, Zepu Zou, Chenxuanyin Ren, Jiayang Wang, Zehua Song, Liang Hu, Bo Liu, Yang Leung, Victor C. M. |
| author_facet | Liu, Jing Ma, Zhenchao Wang, Zepu Zou, Chenxuanyin Ren, Jiayang Wang, Zehua Song, Liang Hu, Bo Liu, Yang Leung, Victor C. M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11430 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Survey on Diffusion Models for Anomaly Detection Liu, Jing Ma, Zhenchao Wang, Zepu Zou, Chenxuanyin Ren, Jiayang Wang, Zehua Song, Liang Hu, Bo Liu, Yang Leung, Victor C. M. Machine Learning Artificial Intelligence 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. |
| title | A Survey on Diffusion Models for Anomaly Detection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.11430 |