Detecting Edge and Node Anomalies with Temporal GNNs
Open Access
- 9 December 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 7-13
Abstract
Computer and social networks can be effectively represented as complex temporal graphs where entities (nodes) keep interconnecting through various relationships (edges), forming evolving structures. Anomaly Detection (AD) in such networks consists of identifying patterns diverging from what is expected or normal. This task is fundamental for the detection of potential threats -- e.g. suspicious connections (edge AD) or misbehaving entities (node AD), and challenging due to the lack of a common definition of anomaly. However, the literature is scarce about solutions to detect node anomalies on temporal graphs. This work addresses three challenges in AD as found in computer and social networks: fast-evolving graph structure, lack of ground truth, and simultaneous presence of anomalous nodes and edges. For this, we propose to use temporal Graph Neural Networks (tGNNs) coupled with specialised AD blocks trained in a self-supervised way. We also embed an attention mechanism providing interpretability to the decision process. We extensively validate the tGNNs on synthetic and real-world datasets showing that they successfully detect both node and edge anomalies simultaneously (around 0.9 of average AUC).Keywords
Funding Information
- European Union - NextGenerationEU - MUR National Recovery and Resilience Plan (SERICS (PE00000014))
This publication has 18 references indexed in Scilit:
- Graph Neural Networks for Intrusion Detection: A SurveyIEEE Access, 2023
- Anomal-E: A self-supervised network intrusion detection system based on graph neural networksKnowledge-Based Systems, 2022
- A PIMS Development Kit for New Personal Data PlatformsIEEE Internet Computing, 2022
- Graph-based deep learning for communication networks: A surveyComputer Communications, 2022
- A Comprehensive Survey on Graph Anomaly Detection With Deep LearningIEEE Transactions on Knowledge and Data Engineering, 2021
- Anomaly Detection on Attributed Networks via Contrastive Self-Supervised LearningIEEE Transactions on Neural Networks and Learning Systems, 2021
- T-GCN: A Temporal Graph Convolutional Network for Traffic PredictionIEEE Transactions on Intelligent Transportation Systems, 2019
- Unified Host and Network Data Set2018
- A Survey on Social Media Anomaly DetectionACM SIGKDD Explorations Newsletter, 2016
- A survey of network anomaly detection techniquesJournal of Network and Computer Applications, 2016