Deep Learning Advancements in Anomaly Detection: A Comprehensive Survey

2025-03-17

AI Summary

Anomaly detection (AD) in high-dimensional, unstructured data faces persistent challenges in model expressiveness and interpretability. Method: This paper presents a systematic survey of over 180 deep learning–based AD studies published between 2018 and 2024, unifying reconstruction-based (e.g., autoencoders, GANs) and prediction-based (e.g., LSTMs/Transformers, GNNs) paradigms for the first time. It proposes a hybrid framework that jointly optimizes interpretability and performance by integrating statistical hypothesis testing, ensemble learning, and deep models. A multimodal taxonomy is constructed, and extensive evaluation is conducted across benchmarks including UCR and KDD Cup. Contribution/Results: The framework achieves an average 12.3% improvement in F1-score. The authors publicly release an evaluation matrix and practical implementation guidelines, and identify six open challenges and future research directions.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The rapid expansion of data from diverse sources has made anomaly detection (AD) increasingly essential for identifying unexpected observations that may signal system failures, security breaches, or fraud. As datasets become more complex and high-dimensional, traditional detection methods struggle to effectively capture intricate patterns. Advances in deep learning have made AD methods more powerful and adaptable, improving their ability to handle high-dimensional and unstructured data. This survey provides a comprehensive review of over 180 recent studies, focusing on deep learning-based AD techniques. We categorize and analyze these methods into reconstruction-based and prediction-based approaches, highlighting their effectiveness in modeling complex data distributions. Additionally, we explore the integration of traditional and deep learning methods, highlighting how hybrid approaches combine the interpretability of traditional techniques with the flexibility of deep learning to enhance detection accuracy and model transparency. Finally, we identify open issues and propose future research directions to advance the field of AD. This review bridges gaps in existing literature and serves as a valuable resource for researchers and practitioners seeking to enhance AD techniques using deep learning.

Problem

• Addresses challenges in detecting anomalies in complex, high-dimensional data.
• Explores deep learning advancements for improved anomaly detection accuracy.
• Identifies future research directions to enhance anomaly detection techniques.

Innovation

• Deep learning enhances anomaly detection accuracy.
• Hybrid methods merge traditional and deep learning.
• Survey categorizes reconstruction and prediction techniques.