Deep Learning for Anomaly Detection: A Survey

TLDR

Anomaly detection is a well‑studied problem across diverse research areas and application domains. This survey aims to provide a structured overview of deep learning‑based anomaly detection methods and evaluate their adoption and effectiveness across various application domains. The survey categorizes deep learning anomaly detection techniques, outlines their assumptions, variants, advantages, limitations, computational complexity, and discusses open research issues and adoption challenges. State‑of‑the‑art deep learning anomaly detection techniques are grouped into categories defined by their underlying assumptions and approaches.

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.