Deep Learning for Anomaly Detection: A Survey
Raghavendra Chalapathy, Sanjay Chawla
TL;DR
This survey addresses the challenge of detecting anomalies in complex, large-scale data by organizing deep learning approaches into a coherent taxonomy. It introduces two new categories, Deep Hybrid Models (DHM) and One-Class Neural Networks (OC-NN), and analyzes methods across input data types, label availability, training objectives, and anomaly types. The paper surveys a broad spectrum of applications, from intrusion and fraud detection to medical and industrial domains, and discusses computational considerations, strengths, and limitations of each approach. It also outlines open issues and future directions, providing practical guidance for selecting DAD methods in real-world settings.
Abstract
Anomaly detection is an important problem that has been well-studied within diverse research areas and application domains. The aim of this survey is two-fold, firstly we present a structured and comprehensive overview of research methods in deep learning-based anomaly detection. Furthermore, we review the adoption of these methods for anomaly across various application domains and assess their effectiveness. We have grouped state-of-the-art research techniques into different categories based on the underlying assumptions and approach adopted. Within each category we outline the basic anomaly detection technique, along with its variants and present key assumptions, to differentiate between normal and anomalous behavior. For each category, we present we also present the advantages and limitations and discuss the computational complexity of the techniques in real application domains. Finally, we outline open issues in research and challenges faced while adopting these techniques.