A Survey on Diffusion Models for Anomaly Detection

TL;DR

Diffusion models have recently been applied to anomaly detection across various domains, with this survey reviewing recent advances, architectures, methodologies, and challenges in the field of diffusion models for anomaly detection.

Contribution

This paper provides a comprehensive review of diffusion models for anomaly detection, categorizing methods, analyzing architectures, and discussing future research directions.

Findings

Categorization of DMAD methods into reconstruction, density, and hybrid approaches.

Analysis of architectures like DDPMs, DDIMs, and Score SDEs.

Identification of key challenges such as efficiency, interpretability, and robustness.

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 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.