Graphfool: Targeted Label Adversarial Attack on Graph Embedding

TL;DR

Graphfool is a novel targeted adversarial attack method on graph embedding models, effectively generating minimal perturbations to mislead deep graph analysis techniques, outperforming existing methods.

Contribution

This paper introduces Graphfool, the first targeted label attack technique on graph embedding, leveraging boundary estimation and gradient-based perturbations.

Findings

Graphfool achieves an 11.44% higher success rate than previous methods.

It effectively misleads graph embedding models with minimal perturbations.

Experimental results on real-world graphs validate its superior performance.

Abstract

Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classification etc. Graph embedding, which learns low-dimensional representations for vertices or edges in the graph, usually employs deep models to derive the embedding vector. However, these models are vulnerable. We envision that graph embedding methods based on deep models can be easily attacked using adversarial examples. Thus, in this paper, we propose Graphfool, a novel targeted label adversarial attack on graph embedding. It can generate adversarial graph to attack graph embedding methods via classifying boundary and gradient information in graph convolutional network (GCN). Specifically, we perform the following steps: 1),We first estimate the classification boundaries of different classes. 2), We calculate the minimal perturbation matrix to misclassify the attacked vertex according to the target classification boundary. 3), We modify the adjacency matrix according to the maximal absolute value of the disturbance matrix. This process is implemented iteratively. To the best of our knowledge, this is the first targeted label attack technique. The experiments on real-world graph networks demonstrate that Graphfool can derive better performance than state-of-art techniques. Compared with the second best algorithm, Graphfool can achieve an average improvement of 11.44% in attack success rate.