Node Injection Attacks on Graphs via Reinforcement Learning
This addresses security vulnerabilities in real-world graph applications like advertisements and recommendations, where adversaries can degrade classification performance, representing an incremental advance in adversarial attack methods.
The paper tackles the problem of poisoning graph-based node classification systems by injecting adversarial nodes, which is more practical than modifying existing structures, and demonstrates that their reinforcement learning method NIPA outperforms state-of-the-art methods on benchmark datasets.
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.