Abstract

Anomaly detection is an important task, which tackles the problem of discovering “different from normal” signals or patterns by analyzing a massive amount of data, thereby identifying and preventing major faults. Anomaly detection is applied to numerous high-impact applications in areas such as cyber-security, finance, e-commerce, social network, industrial monitoring, and many more mission-critical tasks. While multiple techniques have been developed in past decades in addressing unstructured collections of multi-dimensional data, graph-structure-aware techniques have recently attracted considerable attention. A number of novel techniques have been developed for anomaly detection by leveraging the graph structure. Recently, graph neural networks (GNNs), as a powerful deep-learning-based graph representation technique, has demonstrated superiority in leveraging the graph structure and been used in anomaly detection. In this chapter, we provide a general, comprehensive, and structured overview of the existing works that apply GNNs in anomaly detection.

Contents

• Introduction
• Issues
• Data-specific issues
• Task-specific issues
• Model-specific issues
• Pipeline
• Graph Construction and Transformation
• Graph Representation Learning
• Prediction
• Taxonomy
• Case Studies
• Case Study: Graph Embeddings for Malicious Accounts Detection
• Case Study: Hierarchical Attention Mechanism based Cash-out User Detection
• Case Study: Attention Heterogeneous Graph Neural Network for Malicious Program Detection
• Case Study: Graph Matching Framework to Learn the Program Representation and Similarity Metric via Graph Neural Network for Unknown Malicious Program Detection
• Case Study: Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN
• Case Study: GCN-based Anti-Spam for Spam Review Detection
• Future Directions

Citation