A Survey on Diffusion Models for Anomaly Detection

2025-01-20

AI Summary

This paper addresses the lack of systematic taxonomy and methodological guidance for applying diffusion models (DMs) to anomaly detection (AD). To this end, we propose DMAD—the first taxonomy specifically designed for DM-based AD—categorizing existing approaches into three unified paradigms: reconstruction-based, density-based, and hybrid methods. We systematically analyze the applicability and limitations of mainstream DM architectures—including DDPM, DDIM, and Score SDE—across diverse data modalities (images, time series, videos, and multimodal inputs). Innovatively, we introduce novel paradigms such as edge-cloud collaborative inference and large-model integration to enhance interpretability and robustness. Furthermore, we release an open-source literature repository and resource checklist on GitHub, establishing the first unified research framework for DMAD. This work provides both a theoretical benchmark for academia and a practical, deployable technology roadmap for industry.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

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 systematically review recent advances in DMAD research and investigate their capabilities. 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.

Problem

• Anomaly Detection
• Diffusion Models
• Complex Data

Innovation

• Diffusion Models
• Anomaly Detection
• Interdisciplinary Application