SPEAR: A Structure-Preserving Manipulation Method for Graph Backdoor Attacks

Yuanhao Ding, Yang Liu, Yugang Ji, Weigao Wen, Qing He, Xiang Ao

Track: Graph algorithms and modeling for the Web

Keywords: Adversarial Attack, Backdoor Attack, Graph Neural Network

Abstract: Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing graph backdoor attacks are susceptible to defense mechanisms or robust classifiers because they rely on subgraph injection or structural perturbations, e.g., creating additional edges to attach backdoor triggers to the original graph. To enhance the stealthiness of graph backdoors, we propose SPEAR, a novel structure-preserving graph backdoor attack that avoids modifying the graph’s topology. SPEAR operates within a limited attack budget by selectively perturbing node attributes while ensuring the triggers exert significant influence through a global importance-driven feature selection strategy. Additionally, a neighborhood-aware trigger generator is employed to underpin a high attack success rate by utilizing semantic information from the neighborhood. SPEAR amplifies effectiveness and stealthiness by combining subtle yet impactful attribute manipulation with a refined trigger generation mechanism. Extensive experiments demonstrate that SPEAR achieves state-of-the-art effectiveness in bypassing defenses on real-world datasets, establishing it as a potent and stealthy backdoor attack for graph-based tasks.

Submission Number: 1867