Fast Gradient Attack on Network Embedding

Abstract

Network embedding maps a network into a low-dimensional Euclidean space, and thus facilitate many network analysis tasks, such as node classification, link prediction and community detection etc, by utilizing machine learning methods. In social networks, we may pay special attention to user privacy, and would like to prevent some target nodes from being identified by such network analysis methods in certain cases. Inspired by successful adversarial attack on deep learning models, we propose a framework to generate adversarial networks based on the gradient information in Graph Convolutional Network (GCN). In particular, we extract the gradient of pairwise nodes based on the adversarial network, and select the pair of nodes with maximum absolute gradient to realize the Fast Gradient Attack (FGA) and update the adversarial network. This process is implemented iteratively and terminated until certain condition is satisfied, i.e., the number of modified links reaches certain predefined value. Comprehensive attacks, including unlimited attack, direct attack and indirect attack, are performed on six well-known network embedding methods. The experiments on real-world networks suggest that our proposed FGA behaves better than some baseline methods, i.e., the network embedding can be easily disturbed using FGA by only rewiring few links, achieving state-of-the-art attack performance.

References in corpus (8)

• Efficient Estimation of Word Representations in Vector Space
• Semi-Supervised Classification with Graph Convolutional Networks
• Lethality and centrality in protein networks
• Adversarial Attacks on Neural Networks for Graph Data
• Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
• GraphGAN: Graph Representation Learning with Generative Adversarial Nets
• Adversarial Network Embedding
• From Node Embedding To Community Embedding

Cited by in corpus (32)

• Adversarial Attack and Defense on Graph Data: A Survey
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Prediction
• DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses
• A Survey of Adversarial Learning on Graphs
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Node Injection Attacks on Graphs via Reinforcement Learning
• Link Prediction Adversarial Attack
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Can Adversarial Network Attack be Defended?
• Single-Node Attacks for Fooling Graph Neural Networks
• Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
• Towards More Practical Adversarial Attacks on Graph Neural Networks
• Time-aware Gradient Attack on Dynamic Network Link Prediction
• Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation
• Data Poisoning Attack against Knowledge Graph Embedding
• GraphAttacker: A General Multi-Task GraphAttack Framework
• Multiscale Evolutionary Perturbation Attack on Community Detection
• Unsupervised Euclidean Distance Attack on Network Embedding
• Node Copying: A Random Graph Model for Effective Graph Sampling
• Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection
• Robustness of Graph Neural Networks at Scale
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
• Auditing the Sensitivity of Graph-based Ranking with Visual Analytics
• N2VSCDNNR: A Local Recommender System Based on Node2vec and Rich Information Network
• EGC2: Enhanced Graph Classification with Easy Graph Compression
• DeepInsight: Interpretability Assisting Detection of Adversarial Samples on Graphs
• PredCoin: Defense against Query-based Hard-label Attack
• GA Based Q-Attack on Community Detection
• MGA: Momentum Gradient Attack on Network