GraphAttacker: A General Multi-Task GraphAttack Framework

Abstract

Graph neural networks (GNNs) have been successfully exploited in graph analysis tasks in many real-world applications. The competition between attack and defense methods also enhances the robustness of GNNs. In this competition, the development of adversarial training methods put forward higher requirement for the diversity of attack examples. By contrast, most attack methods with specific attack strategies are difficult to satisfy such a requirement. To address this problem, we propose GraphAttacker, a novel generic graph attack framework that can flexibly adjust the structures and the attack strategies according to the graph analysis tasks. GraphAttacker generates adversarial examples through alternate training on three key components: the multi-strategy attack generator (MAG), the similarity discriminator (SD), and the attack discriminator (AD), based on the generative adversarial network (GAN). Furthermore, we introduce a novel similarity modification rate SMR to conduct a stealthier attack considering the change of node similarity distribution. Experiments on various benchmark datasets demonstrate that GraphAttacker can achieve state-of-the-art attack performance on graph analysis tasks of node classification, graph classification, and link prediction, no matter the adversarial training is conducted or not. Moreover, we also analyze the unique characteristics of each task and their specific response in the unified attack framework. The project code is available at https://github.com/honoluluuuu/GraphAttacker.

arXiv comment17 pages,9 figeures

References in corpus (29)

• Semi-Supervised Classification with Graph Convolutional Networks
• Fast algorithm for detecting community structure in networks
• Finding community structure in networks using the eigenvectors of matrices
• Inductive Representation Learning on Large Graphs
• Link Prediction in Complex Networks: A Survey
• Adversarial Attacks on Neural Networks for Graph Data
• Variational Graph Auto-Encoders
• Hierarchical Graph Representation Learning with Differentiable Pooling
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Strategies for Pre-training Graph Neural Networks
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• Fast Gradient Attack on Network Embedding
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• T-EDGE: Temporal WEighted MultiDiGraph Embedding for Ethereum Transaction Network Analysis
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Attack Graph Convolutional Networks by Adding Fake Nodes
• Certifiable Robustness to Graph Perturbations
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks
• Link Prediction Adversarial Attack
• GraphSAC: Detecting anomalies in large-scale graphs
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Can Adversarial Network Attack be Defended?
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Time-aware Gradient Attack on Dynamic Network Link Prediction
• Heterogeneous Graph Matching Networks
• Adversarial Recommendation: Attack of the Learned Fake Users

Cited by in corpus (2)

• Node Injection Attack Based on Label Propagation Against Graph Neural Network
• Adversarial Attacks on Graph Classification via Bayesian Optimisation