Article citationsMore>>

Le, H.D. and Park, M. (2024) Enhancing Multi-Class Attack Detection in Graph Neural Network through Feature Rearrangement. Electronics, 13, Article 2404.
https://doi.org/10.3390/electronics13122404

has been cited by the following article:

• TITLE: Graph Neural Networks for Anomaly Detection in Cloud Infrastructure

  AUTHORS: Adithya Jakkaraju

  KEYWORDS: Graph Neural Networks, Anomaly Detection, Cloud Infrastructure, Temporal Graph Convolution, Graph Autoencoder, Microservice Dependencies, Telemetry Fusion

  JOURNAL NAME: Journal of Computer and Communications, Vol.13 No.10, October 22, 2025

  ABSTRACT: Cloud infrastructure anomalies cause significant downtime and financial losses (estimated at $2.5 M/hour for major services). Traditional anomaly detection methods fail to capture complex dependencies in microservice architectures. This paper presents a novel Temporal-Attentive Graph Autoencoder (TAGAE) framework for cloud anomaly detection, leveraging Graph Neural Networks (GNNs) to model topological relationships and temporal dynamics. Our method integrates multi-source telemetry (logs, metrics, and traces) into a unified graph structure, utilizes anomaly amplification layers for enhanced sensitivity, and employs focal loss for data imbalance mitigation. Evaluated on Azure-DIAD and GCP datasets, TAGAE achieves 94.2% F1-score and 96.5% AUC-PR, reducing detection latency by 63% compared to GraphSAGE. We further analyze robustness under 40% noise/missing data and propose federated GNNs for privacy-preserving deployment.