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.

翻译：扩散模型已成为一类强大的生成式人工智能模型，在网络安全、欺诈检测、医疗健康和制造业等多个领域的异常检测任务中展现出卓越潜力。这两个领域的交叉——即用于异常检测的扩散模型——为识别日益复杂的高维数据中的偏差提供了前景广阔的解决方案。本综述系统回顾了DMAD研究的最新进展。我们首先阐述异常检测与扩散模型的基本概念，随后对包括DDPM、DDIM和Score SDE在内的经典扩散模型架构进行全面解析。我们将现有DMAD方法进一步划分为基于重构、基于密度和混合方法三大类别，并深入剖析其方法论创新。同时，我们探讨了涵盖图像、时间序列、视频及多模态数据分析等不同数据模态的多样化任务。此外，本文讨论了关键挑战与新兴研究方向，包括计算效率、模型可解释性、鲁棒性增强、边云协同以及与大型语言模型的融合。相关研究论文与资源集可通过https://github.com/fdjingliu/DMAD获取。