Research on Anomaly Detection Methods Based on Diffusion Models

TL;DR

This paper introduces a novel anomaly detection framework using diffusion probabilistic models that effectively identify anomalies in image and audio data by modeling normal data distributions and leveraging advanced feature extraction techniques.

Contribution

The study presents a new diffusion model-based approach for anomaly detection, incorporating multi-scale features, attention, and wavelet representations to improve detection accuracy and robustness.

Findings

Outperforms existing anomaly detection methods on benchmark datasets.

Achieves higher accuracy and robustness across image and audio modalities.

Effectively captures fine-grained and global data structures.

Abstract

Anomaly detection is a fundamental task in machine learning and data mining, with significant applications in cybersecurity, industrial fault diagnosis, and clinical disease monitoring. Traditional methods, such as statistical modeling and machine learning-based approaches, often face challenges in handling complex, high-dimensional data distributions. In this study, we explore the potential of diffusion models for anomaly detection, proposing a novel framework that leverages the strengths of diffusion probabilistic models (DPMs) to effectively identify anomalies in both image and audio data. The proposed method models the distribution of normal data through a diffusion process and reconstructs input data via reverse diffusion, using a combination of reconstruction errors and semantic discrepancies as anomaly indicators. To enhance the framework's performance, we introduce multi-scale feature extraction, attention mechanisms, and wavelet-domain representations, enabling the model to capture fine-grained structures and global dependencies in the data. Extensive experiments on benchmark datasets, including MVTec AD and UrbanSound8K, demonstrate that our method outperforms state-of-the-art anomaly detection techniques, achieving superior accuracy and robustness across diverse data modalities. This research highlights the effectiveness of diffusion models in anomaly detection and provides a robust and efficient solution for real-world applications.