Single-Edge Node Injection Threats to GNN-Based Security Monitoring in Industrial Graph Systems

2026-02-01

AI Summary

This work addresses the vulnerability of industrial graph neural networks (GNNs) to resource-constrained node injection attacks. It formally introduces single-edge graph injection attacks (SEGIA), wherein an adversary injects fake nodes using only a single edge per node under a strict edge budget to evade detection and disrupt decision-making. To realize SEGIA, the authors propose an attack strategy integrating a pruned SGC surrogate, multi-hop neighborhood sampling, and reverse graph convolution for feature synthesis, which preserves local homophily while enhancing robustness against edge pruning. Extensive experiments demonstrate that SEGIA achieves at least a 25% higher attack success rate than existing methods across multiple datasets and defense mechanisms, while consuming fewer edge resources, thereby exposing systemic security risks in deployed industrial GNN systems.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements

Abstract

Graph neural networks (GNNs) are increasingly adopted in industrial graph-based monitoring systems (e.g., Industrial internet of things (IIoT) device graphs, power-grid topology models, and manufacturing communication networks) to support anomaly detection, state estimation, and asset classification. In such settings, an adversary that compromises a small number of edge devices may inject counterfeit nodes (e.g., rogue sensors, virtualized endpoints, or spoofed substations) to bias downstream decisions while evading topology- and homophily-based sanitization. This paper formulates deployment-oriented node-injection attacks under constrained resources and proposes the \emph{Single-Edge Graph Injection Attack} (SEGIA), in which each injected node attaches to the operational graph through a single edge. SEGIA integrates a pruned SGC surrogate, multi-hop neighborhood sampling, and reverse graph convolution-based feature synthesis with a similarity-regularized objective to preserve local homophily and survive edge pruning. Theoretical analysis and extensive evaluations across datasets and defenses show at least $25\%$ higher attack success than representative baselines under substantially smaller edge budgets. These results indicate a system-level risk in industrial GNN deployments and motivate lightweight admission validation and neighborhood-consistency monitoring.

Problem

• node injection attack
• graph neural networks
• industrial graph systems
• security monitoring
• single-edge injection

Innovation

• Single-Edge Injection
• Graph Neural Networks
• Adversarial Attack
• Homophily Preservation
• Industrial Graph Systems