Neighboring Backdoor Attacks on Graph Convolutional Network

TL;DR

This paper introduces a novel graph-specific backdoor attack called neighboring backdoor, which activates when a trigger node connects to a target node, achieving high success without affecting normal model performance.

Contribution

The paper proposes the first neighboring backdoor attack for graph neural networks, designing trigger nodes and features without modifying model parameters, and extends existing attack methods to this setting.

Findings

Achieves nearly 100% attack success rate.

No impact on model accuracy during normal operation.

Effective on social and citation network datasets.

Abstract

Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their success in the conventional Euclidean space, there are few studies of backdoor attacks on graph structured data. In this paper, we propose a new type of backdoor which is specific to graph data, called neighboring backdoor. Considering the discreteness of graph data, how to effectively design the triggers while retaining the model accuracy on the original task is the major challenge. To address such a challenge, we set the trigger as a single node, and the backdoor is activated when the trigger node is connected to the target node. To preserve the model accuracy, the model parameters are not allowed to be modified. Thus, when the trigger node is not connected, the model performs normally. Under these settings, in this work, we focus on generating the features of the trigger node. Two types of backdoors are proposed: (1) Linear Graph Convolution Backdoor which finds an approximation solution for the feature generation (can be viewed as an integer programming problem) by looking at the linear part of GCNs. (2) Variants of existing graph attacks. We extend current gradient-based attack methods to our backdoor attack scenario. Extensive experiments on two social networks and two citation networks datasets demonstrate that all proposed backdoors can achieve an almost 100\% attack success rate while having no impact on predictive accuracy.