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

TL;DR

This paper introduces SEGIA, a novel attack method exploiting single-edge node injections in industrial GNN systems, revealing significant vulnerabilities and emphasizing the need for improved security measures.

Contribution

It formulates a new resource-constrained node-injection attack (SEGIA) and demonstrates its effectiveness over existing methods in industrial GNN applications.

Findings

SEGIA achieves at least 25% higher attack success than baselines.

Attacks require fewer edges, demonstrating efficiency.

Results highlight vulnerabilities in industrial GNN deployments.

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.