aiqbench analysis
This survey synthesizes the synergistic relationship between diffusion models and anomaly detection, demonstrating how generative capabilities can overcome data scarcity while detection feedback refines generation fidelity. It provides a comprehensive taxonomy of methods across images, time series, and multimodal data, while addressing critical challenges like scalability and computational efficiency for real-world deployment. By integrating insights from foundation models, the paper outlines a clear path forward for researchers aiming to build robust unsupervised anomaly detection systems.
Anomaly Detection and Generation with Diffusion Models: A Survey
arXiv:2506.09368v2 Announce Type: replace-cross Abstract: Anomaly detection (AD) plays a pivotal role across diverse domains, including cybersecurity, finance, healthcare, and industrial manufacturing, by identifying unexpected patterns that deviate from established norms in real-world data. Recent advancements in deep learning, specifically diffusion models (DMs), have sparked significant interest due to their ability to learn complex data distributions and generate high-fidelity samples, offering a robust framework for unsupervised AD. In this survey, we comprehensively review anomaly detection and generation with diffusion models (ADGDM), presenting a tutorial-style analysis of the theoretical foundations and practical implementations and spanning images, videos, time series, tabular, and multimodal data. Crucially, unlike existing surveys that often treat anomaly detection and generation as separate problems, we highlight their inherent synergistic relationship. We reveal how DMs enable a reinforcing cycle where generation techniques directly address the fundamental challenge of anomaly data scarcity, while detection methods provide critical feedback to improve generation fidelity and relevance, advancing both capabilities beyond their individual potential. A detailed taxonomy categorizes ADGDM methods based on anomaly scoring mechanisms, conditioning strategies, and architectural designs, analyzing their strengths and limitations. We final discuss key challenges including scalability and computational efficiency, and outline promising future directions such as efficient architectures, conditioning strategies, and integration with foundation models (e.g., visual-language models and large language models). By synthesizing recent advances and outlining open research questions, this survey aims to guide researchers and practitioners in leveraging DMs for innovative AD solutions across diverse applications.
Abstract:Anomaly detection (AD) plays a pivotal role across diverse domains, including cybersecurity, finance, healthcare, and industrial manufacturing, by identifying unexpected patterns that deviate from established norms in real-world data. Recent advancements in deep learning, specifically diffusion models (DMs), have sparked significant interest due to their ability to learn complex data distributions and generate high-fidelity samples, offering a robust framework for unsupervised AD. In this survey, we comprehensively review anomaly detection and generation with diffusion models (ADGDM), presenting a tutorial-style analysis of the theoretical foundations and practical implementations and spanning images, videos, time series, tabular, and multimodal data. Crucially, unlike existing surveys that often treat anomaly detection and generation as separate problems, we highlight their inherent synergistic relationship. We reveal how DMs enable a reinforcing cycle where generation techniques directly address the fundamental challenge of anomaly data scarcity, while detection methods provide critical feedback to improve generation fidelity and relevance, advancing both capabilities beyond their individual potential. A detailed taxonomy categorizes ADGDM methods based on anomaly scoring mechanisms, conditioning strategies, and architectural designs, analyzing their strengths and limitations. We final discuss key challenges including scalability and computational efficiency, and outline promising future directions such as efficient architectures, conditioning strategies, and integration with foundation models (e.g., visual-language models and large language models). By synthesizing recent advances and outlining open research questions, this survey aims to guide researchers and practitioners in leveraging DMs for innovative AD solutions across diverse applications.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2506.09368 [cs.LG]
(or arXiv:2506.09368v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2506.09368 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1109/TPAMI.2026.3739960 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 342 words
Related coverage
Diffusion Models in Medical Image Inpainting: Challenges, Solution Taxonomy, and Future Directions
arXiv · Jul 27, 2026
AI Swiftly Detects and Neutralises 6G Network Threats in Milliseconds
Quantum Zeitgeist · Jun 10, 2026
Unsupervised Brain Anomaly Detection as a Bayesian Inverse Problem with Diffusion Prior
arXiv · Sep 22, 2026
Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
arXiv · Jun 12, 2026