A Comprehensive Survey of Graph-based Deep Learning Approaches for Anomaly Detection in Complex Distributed Systems

Anomaly detection is an important problem for complex distributed systems consisting of hardware and software components. A thorough understanding of the requirements and challenges of anomaly detection for such systems is pivotal to the security of a system, especially for real-world deployment. While there have been many diverse research areas and application domains that deal with the problem, few have attempted to provide an in-depth look at such systems. Most anomaly detection techniques have been specifically developed for certain application domains, while others are more generic. In this survey, we explore the significant potential of graph-based algorithms to identify and mitigate different types of anomalies in complex distributed heterogeneous systems. Our main focus is to provide an in-depth look at graphs when applied on heterogeneous computing devices spread across complex distributed systems. This study analyzes, compares, and contrasts the state-of-the-art research articles in the field. First, we describe the characteristics of the real-world distributed systems and their specific challenges of anomaly detection in such complex networks, such as data and evaluation, nature of the anomalies, and real-world requirements. Later, we discuss why graphs can be leveraged in such systems and the benefits of utilizing graphs. Then we will aptly delve into the state-of-the-art approaches and highlight their strength and weaknesses. Finally, we evaluate and compare these approaches and point out the areas for possible improvements.