A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection
This paper surveys the use of Heterogeneous Graph Neural Networks (HGNNs) for anomaly detection in cybersecurity. It addresses the limitations of traditional graph-based methods in handling complex, evolving cyber data. The survey categorizes existing HGNN approaches, reviews their applications, and discusses common datasets and evaluation metrics. Finally, it outlines future research directions to improve the scalability and interpretability of these models. AI
IMPACT Provides a structured overview of HGNN applications in cybersecurity, guiding future research and development in threat detection.