Adversarial Attack on Hierarchical Graph Pooling Neural Networks

Abstract

Recent years have witnessed the emergence and development of graph neural networks (GNNs), which have been shown as a powerful approach for graph representation learning in many tasks, such as node classification and graph classification. The research on the robustness of these models has also started to attract attentions in the machine learning field. However, most of the existing work in this area focus on the GNNs for node-level tasks, while little work has been done to study the robustness of the GNNs for the graph classification task. In this paper, we aim to explore the vulnerability of the Hierarchical Graph Pooling (HGP) Neural Networks, which are advanced GNNs that perform very well in the graph classification in terms of prediction accuracy. We propose an adversarial attack framework for this task. Specifically, we design a surrogate model that consists of convolutional and pooling operators to generate adversarial samples to fool the hierarchical GNN-based graph classification models. We set the preserved nodes by the pooling operator as our attack targets, and then we perturb the attack targets slightly to fool the pooling operator in hierarchical GNNs so that they will select the wrong nodes to preserve. We show the adversarial samples generated from multiple datasets by our surrogate model have enough transferability to attack current state-of-art graph classification models. Furthermore, we conduct the robust train on the target models and demonstrate that the retrained graph classification models are able to better defend against the attack from the adversarial samples. To the best of our knowledge, this is the first work on the adversarial attack against hierarchical GNN-based graph classification models.

References in corpus (21)

• Fast unfolding of communities in large networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Deep Convolutional Networks on Graph-Structured Data
• Simplifying Graph Convolutional Networks
• Adversarial Attacks on Neural Networks for Graph Data
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Adversarial Attack and Defense on Graph Data: A Survey
• Hierarchy measure for complex networks
• Adversarial Attack on Graph Structured Data
• Fast Gradient Attack on Network Embedding
• Hierarchical Graph Pooling with Structure Learning
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
• Attacking Graph Convolutional Networks via Rewiring
• Data Poisoning Attack against Unsupervised Node Embedding Methods
• AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
• Link Prediction Adversarial Attack
• Deep Graph Similarity Learning: A Survey
• Predicting Semantic Relations using Global Graph Properties

Cited by in corpus (8)

• Adversarial Attack and Defense on Graph Data: A Survey
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Projective Ranking-based GNN Evasion Attacks
• Adversarial Attacks on Graph Classification via Bayesian Optimisation
• GraphAttacker: A General Multi-Task GraphAttack Framework
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• A Targeted Universal Attack on Graph Convolutional Network
• EGC2: Enhanced Graph Classification with Easy Graph Compression