Node Injection Attacks on Graphs via Reinforcement Learning

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.

arXiv commentPreprint, under review

References in corpus (10)

• Emergence of scaling in random networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Trust Region Policy Optimization
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Is feature selection secure against training data poisoning?
• NetGAN: Generating Graphs via Random Walks
• Adversarial Attack on Graph Structured Data
• Fast Gradient Attack on Network Embedding
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Adversarial Policies: Attacking Deep Reinforcement Learning

Cited by in corpus (11)

• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
• Towards More Practical Adversarial Attacks on Graph Neural Networks
• Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks
• Learning Transferable Adversarial Examples via Ghost Networks
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection
• A Targeted Universal Attack on Graph Convolutional Network
• Scalable Attack on Graph Data by Injecting Vicious Nodes
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks