Node Injection Attacks on Graphs via Reinforcement Learning

TL;DR

This paper introduces NIPA, a reinforcement learning approach for node injection attacks on graphs, demonstrating its effectiveness in reducing classification accuracy compared to existing methods.

Contribution

The paper presents a novel reinforcement learning-based method for node injection attacks, addressing a more practical attack scenario in real-world graph applications.

Findings

NIPA outperforms existing attack methods on benchmark datasets.

Injected nodes successfully degrade node classification performance.

Reinforcement learning effectively guides adversarial node injection.

Abstract

Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes. However, in such scenarios, there are high incentives for the adversaries to attack such graph to reduce the node classification performance. Previous work on graph adversarial attacks focus on modifying existing graph structures, which is infeasible in most real-world applications. In contrast, it is more practical to inject adversarial nodes into existing graphs, which can also potentially reduce the performance of the classifier. In this paper, we study the novel node injection poisoning attacks problem which aims to poison the graph. We describe a reinforcement learning based method, namely NIPA, to sequentially modify the adversarial information of the injected nodes. We report the results of experiments using several benchmark data sets that show the superior performance of the proposed method NIPA, relative to the existing state-of-the-art methods.