Adversarial Attack on Graph Structured Data

Abstract

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool the model by modifying the combinatorial structure of data. We first propose a reinforcement learning based attack method that learns the generalizable attack policy, while only requiring prediction labels from the target classifier. Also, variants of genetic algorithms and gradient methods are presented in the scenario where prediction confidence or gradients are available. We use both synthetic and real-world data to show that, a family of Graph Neural Network models are vulnerable to these attacks, in both graph-level and node-level classification tasks. We also show such attacks can be used to diagnose the learned classifiers.

arXiv commentto appear in ICML 2018

References in corpus (12)

• Semi-Supervised Classification with Graph Convolutional Networks
• Intriguing properties of neural networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Learning Combinatorial Optimization Algorithms over Graphs
• Adversarial Attacks on Neural Networks for Graph Data
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Gated Graph Sequence Neural Networks
• Adversarial Examples for Evaluating Reading Comprehension Systems
• Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
• Practical Black-Box Attacks against Machine Learning
• Deriving Neural Architectures from Sequence and Graph Kernels

Cited by in corpus (66)

• Adversarial Attacks on Neural Networks for Graph Data
• Graph Contrastive Learning with Augmentations
• Adversarial Attack and Defense on Graph Data: A Survey
• Graph Vulnerability and Robustness: A Survey
• Graph Convolutional Networks for Graphs Containing Missing Features
• Graph Information Bottleneck
• Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• Subgraph Federated Learning with Missing Neighbor Generation
• When Does Self-Supervision Help Graph Convolutional Networks?
• A Survey of Adversarial Learning on Graphs
• Graph Structure Learning for Robust Graph Neural Networks
• Batch Virtual Adversarial Training for Graph Convolutional Networks
• Data Poisoning Attack against Unsupervised Node Embedding Methods
• Recent Advances in Adversarial Training for Adversarial Robustness
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Node Injection Attacks on Graphs via Reinforcement Learning
• Adversarial Attacks on Machine Learning Systems for High-Frequency Trading
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Reliable Graph Neural Networks via Robust Aggregation
• Link Prediction Adversarial Attack
• Recent advances in deep learning theory
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Adversarial Defense Framework for Graph Neural Network
• Can Adversarial Network Attack be Defended?
• DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder
• Structack: Structure-based Adversarial Attacks on Graph Neural Networks
• Goal-directed graph construction using reinforcement learning
• Towards More Practical Adversarial Attacks on Graph Neural Networks
• Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
• Adversarially Regularized Graph Attention Networks for Inductive Learning on Partially Labeled Graphs
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Information Obfuscation of Graph Neural Networks
• Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
• Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing
• Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
• Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models
• Data Poisoning Attack against Knowledge Graph Embedding
• Jointly Attacking Graph Neural Network and its Explanations
• On Training Robust PDF Malware Classifiers
• Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks
• Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
• Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
• Adversarial Attack on Network Embeddings via Supervised Network Poisoning
• Nudge Attacks on Point-Cloud DNNs
• Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
• Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
• Scalable Attack on Graph Data by Injecting Vicious Nodes
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
• Robustness of Graph Neural Networks at Scale
• QFCNN: Quantum Fourier Convolutional Neural Network
• A Targeted Universal Attack on Graph Convolutional Network
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection
• Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation
• Robustness, Privacy, and Generalization of Adversarial Training
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
• Stacked Graph Filter
• Adversarial Edit Attacks for Tree Data
• Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
• Auditing the Sensitivity of Graph-based Ranking with Visual Analytics
• MGA: Momentum Gradient Attack on Network
• GA Based Q-Attack on Community Detection
• Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers
• Shapley Homology: Topological Analysis of Sample Influence for Neural Networks
• Non-Recursive Graph Convolutional Networks