Foundation Models for Anomaly Detection: Vision and Challenges

2025-02-10

AI Summary

To address the challenge of anomaly detection in high-dimensional, complex data across finance, manufacturing, and healthcare, this paper systematically surveys foundational models (FMs) for this task. We propose the first FM-centric functional tripartite taxonomy—comprising encoder, detector, and explainer—unifying representation learning (e.g., ViT-, LLM-, and multimodal FM-based), zero-/few-shot detection, and visual attribution methods. Further, we establish the first unified analytical framework for FM-powered anomaly detection, explicitly identifying key technical bottlenecks, interpretability limitations, and evolutionary trajectories. Our work fills a critical gap in systematic, cross-domain surveying and methodological integration of FMs for anomaly detection, offering both theoretical foundations and practical guidelines for real-world deployment. (136 words)

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

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
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

As data continues to grow in volume and complexity across domains such as finance, manufacturing, and healthcare, effective anomaly detection is essential for identifying irregular patterns that may signal critical issues. Recently, foundation models (FMs) have emerged as a powerful tool for advancing anomaly detection. They have demonstrated unprecedented capabilities in enhancing anomaly identification, generating detailed data descriptions, and providing visual explanations. This survey presents the first comprehensive review of recent advancements in FM-based anomaly detection. We propose a novel taxonomy that classifies FMs into three categories based on their roles in anomaly detection tasks, i.e., as encoders, detectors, or interpreters. We provide a systematic analysis of state-of-the-art methods and discuss key challenges in leveraging FMs for improved anomaly detection. We also outline future research directions in this rapidly evolving field.

Problem

• Advancing anomaly detection using foundation models
• Classifying FMs as encoders, detectors, interpreters
• Addressing key challenges in FM-based anomaly detection

Innovation

• Foundation models enhance anomaly detection
• Taxonomy classifies FMs as encoders, detectors
• Systematic analysis of state-of-the-art methods