A curated collection of adversarial attack and defense on graph data.
Graph Adversarial Learning/ ├── Attack │ ├── 2017 │ │ ├── Adversarial Sets for Regularising Neural Link Predictors.pdf │ │ └── Practical Attacks Against Graph-based Clustering.pdf │ ├── 2018 │ │ ├── Adversarial Attack on Graph Structured Data.pdf │ │ ├── Adversarial Attacks on Neural Networks for Graph Data.pdf │ │ ├── Attack Tolerance of Link Prediction Algorithms How to Hide Your Relations in a Social Network.pdf │ │ ├── Attacking Similarity-Based Link Prediction in Social Networks.pdf │ │ ├── Data Poisoning Attack against Unsupervised Node Embedding Methods.pdf │ │ ├── Fake Node Attacks on Graph Convolutional Networks.pdf │ │ ├── Fast Gradient Attack on Network Embedding.pdf │ │ └── Hiding Individuals and Communities in a Social Network.pdf │ ├── 2019 │ │ ├── A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning.pdf │ │ ├── Adversarial Attacks on Graph Neural Networks via Meta Learning.pdf │ │ ├── Adversarial Attacks on Node Embeddings via Graph Poisoning.pdf │ │ ├── Adversarial Examples on Graph Data Deep Insights into Attack and Defense.pdf │ │ ├── Attacking Graph Convolutional Networks via Rewiring.pdf │ │ ├── Attacking Graph-based Classification via Manipulating the Graph Structure.pdf │ │ ├── Data Poisoning Attack against Knowledge Graph Embedding.pdf │ │ ├── GA Based Q-Attack on Community Detection.pdf │ │ ├── Generalizable Adversarial Attacks with Latent Variable Perturbation Modeling.pdf │ │ ├── Multiscale Evolutionary Perturbation Attack on Community Detection.pdf │ │ ├── Network Structural Vulnerability A Multi-Objective Attacker Perspective.pdf │ │ ├── PeerNets Exploiting Peer Wisdom Against Adversarial Attacks.pdf │ │ ├── Time-aware Gradient Attack on Dynamic Network Link Prediction.pdf │ │ ├── Topology Attack and Defense for Graph Neural Networks An Optimization Perspective.pdf │ │ ├── Unsupervised Euclidean Distance Attack on Network Embedding.pdf │ │ ├── Vertex Nomination, Consistent Estimation, and Adversarial Modification.pdf │ │ └── αCyber Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model.pdf │ └── 2020 │ ├── A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models.pdf │ ├── Adversarial Attack on Community Detection by Hiding Individuals.pdf │ ├── Adversarial Attack on Hierarchical Graph Pooling Neural Networks.pdf │ ├── Adversarial Attack on Large Scale Graph.pdf │ ├── Adversarial Attacks on Graph Neural Networks Perturbations and their Patterns.pdf │ ├── Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks.pdf │ ├── Adversarial Attacks to Scale-Free Networks Testing the Robustness of Physical Criteria.pdf │ ├── Adversarial Perturbations of Opinion Dynamics in Networks.pdf │ ├── Adversarial attack on BC classification for scale-free networks.pdf │ ├── Attackability Characterization of Adversarial Evasion Attack on Discrete Data.pdf │ ├── Backdoor Attacks to Graph Neural Networks.pdf │ ├── Black-Box Adversarial Attacks on Graph Neural Networks as An Influence Maximization Problem.pdf │ ├── Black-Box Adversarial Attacks on Graph Neural Networks with Limited Node Access.pdf │ ├── Cross Entropy Attack on Deep Graph Infomax.pdf │ ├── Efficient Evasion Attacks to Graph Neural Networks via Influence Function.pdf │ ├── Graph Backdoor.pdf │ ├── Graph Universal Adversarial Attacks A Few Bad Actors Ruin Graph Learning Models.pdf │ ├── Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks.pdf │ ├── Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation.pdf │ ├── Link Prediction Adversarial Attack via Iterative Gradient Attack.pdf │ ├── MGA Momentum Gradient Attack on Network.pdf │ ├── Manipulating Node Similarity Measures in Networks.pdf │ ├── Model Extraction Attacks on Graph Neural Networks- Taxonomy and Realization.pdf │ ├── Network disruption maximizing disagreement and polarization in social networks.pdf │ ├── Non-target-specific Node Injection Attacks on Graph Neural Networks A Hierarchical Reinforcement Learning Approach.pdf │ ├── One Vertex Attack on Graph Neural Networks-based Spatiotemporal Forecasting.pdf │ ├── Practical Adversarial Attacks on Graph Neural Networks.pdf │ ├── Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs.pdf │ ├── Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers.pdf │ ├── Scalable Attack on Graph Data by Injecting Vicious Nodes.pdf │ ├── Security and Privacy in Social Networks and Big Data.pdf │ ├── Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection.pdf │ ├── Single-Node Attack for Fooling Graph Neural Networks.pdf │ └── Stealing Links from Graph Neural Networks.pdf ├── Certification │ ├── 2019 │ │ ├── Certifiable Robustness and Robust Training for Graph Convolutional Networks.pdf │ │ └── Certifiable Robustness to Graph Perturbations.pdf │ └── 2020 │ ├── Abstract Interpretation based Robustness Certification for Graph Convolutional Networks.pdf │ ├── Adversarial Immunization for Improving Certifiable Robustness on Graphs.pdf │ ├── Certifiable Robustness of Graph Convolutional Networks under Structure Perturbations.pdf │ ├── Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing.pdf │ ├── Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing.pdf │ ├── Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks.pdf │ ├── Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation.pdf │ ├── Certifying Robustness of Graph Laplacian Based Semi-Supervised Learning.pdf │ ├── Collective Robustness Certificates.pdf │ ├── Efficient Robustness Certificates for Discrete Data Sparsity-Aware Randomized Smoothing for Graphs, Images and More.pdf │ └── Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning.pdf ├── Defense │ ├── 2017 │ │ └── Adversarial Sets for Regularising Neural Link Predictors.pdf │ ├── 2018 │ │ └── Adversarial Personalized Ranking for Recommendation.pdf │ ├── 2019 │ │ ├── Adversarial Defense Framework for Graph Neural Network.pdf │ │ ├── Adversarial Embedding A robust and elusive Steganography and Watermarking technique.pdf │ │ ├── Adversarial Examples on Graph Data Deep Insights into Attack and Defense.pdf │ │ ├── Adversarial Robustness of Similarity-Based Link Prediction.pdf │ │ ├── Adversarial Training Methods for Network Embedding.pdf │ │ ├── Batch Virtual Adversarial Training for Graph Convolutional Networks.pdf │ │ ├── Can Adversarial Network Attack be Defended.pdf │ │ ├── Characterizing Malicious Edges targeting on Graph Neural Networks.pdf │ │ ├── Comparing and Detecting Adversarial Attacks for Graph Deep Learning.pdf │ │ ├── Edge Dithering for Robust Adaptive Graph Convolutional Networks.pdf │ │ ├── Examining Adversarial Learning against Graph-based IoT Malware Detection Systems.pdf │ │ ├── Graph Adversarial Training Dynamically Regularizing Based on Graph Structure.pdf │ │ ├── Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning.pdf │ │ ├── GraphDefense Towards Robust Graph Convolutional Networks.pdf │ │ ├── GraphSAC Detecting anomalies in large-scale graphs.pdf │ │ ├── Improving Robustness to Attacks Against Vertex Classification.pdf │ │ ├── Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications.pdf │ │ ├── Latent Adversarial Training of Graph Convolution Networks.pdf │ │ ├── Robust Graph Convolutional Networks Against Adversarial Attacks.pdf │ │ ├── Target Defense Against Link-Prediction-Based Attacks via Evolutionary Perturbations.pdf │ │ ├── Topology Attack and Defense for Graph Neural Networks An Optimization Perspective.pdf │ │ ├── Virtual Adversarial Training on Graph Convolutional Networks in Node Classification.pdf │ │ └── αCyber Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model.pdf │ └── 2020 │ ├── A Feature-Importance-Aware and Robust Aggregator for GCN.pdf │ ├── A Graph Matching Attack on Privacy-Preserving Record Linkage.pdf │ ├── Adversarial Perturbations of Opinion Dynamics in Networks.pdf │ ├── Adversarial Privacy Preserving Graph Embedding against Inference Attack.pdf │ ├── All You Need Is Low (Rank) Defending Against Adversarial Attacks on Graphs.pdf │ ├── Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian.pdf │ ├── DefenseVGAE Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder.pdf │ ├── Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning.pdf │ ├── Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters.pdf │ ├── Evaluating Graph Vulnerability and Robustness using TIGER.pdf │ ├── Friend or Faux Graph-Based Early Detection of Fake Accounts.pdf │ ├── GNNGUARD Defending Graph Neural Networks against Adversarial Attacks.pdf │ ├── Graph Adversarial Networks Protecting Information against Adversarial Attacks.pdf │ ├── Graph Random Neural Networks.pdf │ ├── Graph Structure Learning for Robust Graph Neural Networks.pdf │ ├── How Robust Are Graph Neural Networks to Structural Noise.pdf │ ├── Iterative Deep Graph Learning for Graph Neural Networks Better and Robust Node Embeddings.pdf │ ├── Node Copying for Protection Against Graph Neural Network Topology Attacks.pdf │ ├── On The Stability of Polynomial Spectral Graph Filters.pdf │ ├── On the Robustness of Cascade Diffusion under Node Attacks.pdf │ ├── Power up! Robust Graph Convolutional Network against Evasion Attacks based on Graph Powering.pdf │ ├── Provable Overlapping Community Detection in Weighted Graphs.pdf │ ├── ResGCN Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks.pdf │ ├── Ricci-GNN Defending Against Structural Attacks Through a Geometric Approach.pdf │ ├── RoGAT a robust GNN combined revised GAT with adjusted.pdf │ ├── Robust Collective Classification against Structural Attacks.pdf │ ├── Robust Graph Learning From Noisy Data.pdf │ ├── Robust Graph Representation Learning via Neural Sparsification.pdf │ ├── Robust Spammer Detection by Nash Reinforcement Learning.pdf │ ├── Robust Training of Graph Convolutional Networks via Latent Perturbation.pdf │ ├── Security and Privacy in Social Networks and Big Data.pdf │ ├── Tensor Graph Convolutional Networks for Multi-relational and Robust Learning.pdf │ ├── Topological Effects on Attacks Against Vertex Classification.pdf │ ├── Towards Robust Graph Neural Networks against Label Noise.pdf │ ├── Towards an Efficient and General Framework of Robust Training for Graph Neural Networks.pdf │ ├── Transferring Robustness for Graph Neural Network Against Poisoning Attacks.pdf │ ├── Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks.pdf │ ├── Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks.pdf │ └── Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings.pdf ├── Others │ ├── Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning.pdf │ └── FLAG Adversarial Data Augmentation for Graph Neural Networks.pdf ├── README.txt ├── Resource │ └── KDD2020 Adversarial Attacks and Defenses Frontiers, Advances and Practice.pdf ├── Stability │ ├── Graph Neural Networks Architectures, Stability and Transferability.pdf │ ├── Graph and graphon neural network stability.pdf │ ├── On the Stability of Graph Convolutional Neural Networks under Edge Rewiring.pdf │ ├── Stability Properties of Graph Neural Networks.pdf │ ├── Stability and Generalization of Graph Convolutional Neural Networks.pdf │ ├── Stability of Graph Neural Networks to Relative Perturbations.pdf │ └── When Do GNNs Work Understanding and Improving Neighborhood Aggregation.pdf └── Survey ├── A Survey of Adversarial Learning on Graph.pdf ├── Adversarial Attack and Defense on Graph Data A Survey.pdf ├── Adversarial Attacks and Defenses in Images, Graphs and Text A Review.pdf └── Adversarial Attacks and Defenses on Graphs A Review and Empirical Study.pdf
23 papers
except for
add
Move to defense 2020
16 papers
8 papers
2 papers
28 papers
Add
25 papers Add
1 papers
1 papers
4 papers
Graph Adversarial Learning ├── Attack │ ├── 2017 │ │ ├── Adversarial Sets for Regularising Neural Link Predictors.pdf │ │ └── Practical Attacks Against Graph-based Clustering.pdf │ ├── 2018 │ │ ├── Adversarial Attack on Graph Structured Data.pdf │ │ ├── Adversarial Attacks on Neural Networks for Graph Data.pdf │ │ ├── Attack Tolerance of Link Prediction Algorithms How to Hide Your Relations in a Social Network.pdf │ │ ├── Attacking Similarity-Based Link Prediction in Social Networks.pdf │ │ ├── Data Poisoning Attack against Unsupervised Node Embedding Methods.pdf │ │ ├── Fake Node Attacks on Graph Convolutional Networks.pdf │ │ ├── Fast Gradient Attack on Network Embedding.pdf │ │ └── Hiding Individuals and Communities in a Social Network.pdf │ ├── 2019 │ │ ├── A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning.pdf │ │ ├── Adversarial Attacks on Graph Neural Networks via Meta Learning.pdf │ │ ├── Adversarial Attacks on Node Embeddings via Graph Poisoning.pdf │ │ ├── Adversarial Examples on Graph Data Deep Insights into Attack and Defense.pdf │ │ ├── Attacking Graph Convolutional Networks via Rewiring.pdf │ │ ├── Attacking Graph-based Classification via Manipulating the Graph Structure.pdf │ │ ├── Data Poisoning Attack against Knowledge Graph Embedding.pdf │ │ ├── GA Based Q-Attack on Community Detection.pdf │ │ ├── Generalizable Adversarial Attacks with Latent Variable Perturbation Modeling.pdf │ │ ├── Multiscale Evolutionary Perturbation Attack on Community Detection.pdf │ │ ├── Network Structural Vulnerability A Multi-Objective Attacker Perspective.pdf │ │ ├── Time-aware Gradient Attack on Dynamic Network Link Prediction.pdf │ │ ├── Topology Attack and Defense for Graph Neural Networks An Optimization Perspective.pdf │ │ ├── Unsupervised Euclidean Distance Attack on Network Embedding.pdf │ │ ├── Vertex Nomination, Consistent Estimation, and Adversarial Modification.pdf │ │ └── αCyber Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model.pdf │ └── 2020 │ ├── A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models.pdf │ ├── Adversarial Attack on Community Detection by Hiding Individuals.pdf │ ├── Adversarial Attack on Hierarchical Graph Pooling Neural Networks.pdf │ ├── Adversarial Attacks on Graph Neural Networks Perturbations and their Patterns.pdf │ ├── Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks.pdf │ ├── Adversarial Attacks to Scale-Free Networks Testing the Robustness of Physical Criteria.pdf │ ├── Adversarial Perturbations of Opinion Dynamics in Networks.pdf │ ├── Adversarial attack on BC classification for scale-free networks.pdf │ ├── An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs.pdf │ ├── Attackability Characterization of Adversarial Evasion Attack on Discrete Data.pdf │ ├── Backdoor Attacks to Graph Neural Networks.pdf │ ├── Black-Box Adversarial Attacks on Graph Neural Networks with Limited Node Access.pdf │ ├── Graph Backdoor.pdf │ ├── Graph Universal Adversarial Attacks A Few Bad Actors Ruin Graph Learning Models.pdf │ ├── Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks.pdf │ ├── Link Prediction Adversarial Attack via Iterative Gradient Attack.pdf │ ├── MGA Momentum Gradient Attack on Network.pdf │ ├── Manipulating Node Similarity Measures in Networks.pdf │ ├── Network disruption maximizing disagreement and polarization in social networks.pdf │ ├── Non-target-specific Node Injection Attacks on Graph Neural Networks A Hierarchical Reinforcement Learning Approach.pdf │ ├── Practical Adversarial Attacks on Graph Neural Networks.pdf │ ├── Scalable Attack on Graph Data by Injecting Vicious Nodes.pdf │ └── Stealing Links from Graph Neural Networks.pdf ├── Defense │ ├── 2017 │ │ └── Adversarial Sets for Regularising Neural Link Predictors.pdf │ ├── 2018 │ │ └── Adversarial Personalized Ranking for Recommendation.pdf │ ├── 2019 │ │ ├── Adversarial Defense Framework for Graph Neural Network.pdf │ │ ├── Adversarial Embedding A robust and elusive Steganography and Watermarking technique.pdf │ │ ├── Adversarial Examples on Graph Data Deep Insights into Attack and Defense.pdf │ │ ├── Adversarial Robustness of Similarity-Based Link Prediction.pdf │ │ ├── Batch Virtual Adversarial Training for Graph Convolutional Networks.pdf │ │ ├── Can Adversarial Network Attack be Defended.pdf │ │ ├── Certifiable Robustness and Robust Training for Graph Convolutional Networks.pdf │ │ ├── Certifiable Robustness to Graph Perturbations.pdf │ │ ├── Characterizing Malicious Edges targeting on Graph Neural Networks.pdf │ │ ├── Comparing and Detecting Adversarial Attacks for Graph Deep Learning.pdf │ │ ├── Edge Dithering for Robust Adaptive Graph Convolutional Networks.pdf │ │ ├── Examining Adversarial Learning against Graph-based IoT Malware Detection Systems.pdf │ │ ├── Graph Adversarial Training Dynamically Regularizing Based on Graph Structure.pdf │ │ ├── Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning.pdf │ │ ├── GraphDefense Towards Robust Graph Convolutional Networks.pdf │ │ ├── GraphSAC Detecting anomalies in large-scale graphs.pdf │ │ ├── Improving Robustness to Attacks Against Vertex Classification.pdf │ │ ├── Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications.pdf │ │ ├── Latent Adversarial Training of Graph Convolution Networks.pdf │ │ ├── Robust Graph Convolutional Networks Against Adversarial Attacks.pdf │ │ ├── Target Defense Against Link-Prediction-Based Attacks via Evolutionary Perturbations.pdf │ │ ├── Topology Attack and Defense for Graph Neural Networks An Optimization Perspective.pdf │ │ ├── Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings.pdf │ │ ├── Virtual Adversarial Training on Graph Convolutional Networks in Node Classification.pdf │ │ └── αCyber Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model.pdf │ └── 2020 │ ├── Abstract Interpretation based Robustness Certification for Graph Convolutional Networks.pdf │ ├── Adversarial Immunization for Improving Certifiable Robustness on Graphs.pdf │ ├── Adversarial Perturbations of Opinion Dynamics in Networks.pdf │ ├── All You Need Is Low (Rank) Defending Against Adversarial Attacks on Graphs.pdf │ ├── Certifiable Robustness of Graph Convolutional Networks under Structure Perturbations.pdf │ ├── Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing.pdf │ ├── DefenseVGAE Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder.pdf │ ├── Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning.pdf │ ├── Efficient Robustness Certificates for Discrete Data Sparsity-Aware Randomized Smoothing for Graphs, Images and More.pdf │ ├── Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters.pdf │ ├── Evaluating Graph Vulnerability and Robustness using TIGER.pdf │ ├── Friend or Faux Graph-Based Early Detection of Fake Accounts.pdf │ ├── GNNGUARD Defending Graph Neural Networks against Adversarial Attacks.pdf │ ├── Graph Structure Learning for Robust Graph Neural Networks.pdf │ ├── How Robust Are Graph Neural Networks to Structural Noise.pdf │ ├── Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning.pdf │ ├── On The Stability of Polynomial Spectral Graph Filters.pdf │ ├── On the Robustness of Cascade Diffusion under Node Attacks.pdf │ ├── Power up! Robust Graph Convolutional Network against Evasion Attacks based on Graph Powering.pdf │ ├── Robust Collective Classification against Structural Attacks.pdf │ ├── Robust Graph Learning From Noisy Data.pdf │ ├── Robust Graph Representation Learning via Neural Sparsification.pdf │ ├── Robust Spammer Detection by Nash Reinforcement Learning.pdf │ ├── Robust Training of Graph Convolutional Networks via Latent Perturbation.pdf │ ├── Tensor Graph Convolutional Networks for Multi-relational and Robust Learning.pdf │ ├── Topological Effects on Attacks Against Vertex Classification.pdf │ ├── Towards an Efficient and General Framework of Robust Training for Graph Neural Networks.pdf │ └── Transferring Robustness for Graph Neural Network Against Poisoning Attacks.pdf └── Survey ├── A Survey of Adversarial Learning on Graph.pdf ├── Adversarial Attack and Defense on Graph Data A Survey.pdf ├── Adversarial Attacks and Defenses in Images, Graphs and Text A Review.pdf └── Adversarial Attacks and Defenses on Graphs A Review and Empirical Study.pdf
11 directories, 108 files
21 papers except for
15 papers
8 papers
2 papers
24 papers except for
24 papers
1 papers
1 papers
4 papers
Graph Adversarial Learning ├── Attack │ ├── 2017 │ │ ├── Adversarial Sets for Regularising Neural Link Predictors.pdf │ │ └── Practical Attacks Against Graph-based Clustering.pdf │ ├── 2018 │ │ ├── Adversarial Attack on Graph Structured Data.pdf │ │ ├── Adversarial Attacks on Neural Networks for Graph Data.pdf │ │ ├── Attack Tolerance of Link Prediction Algorithms How to Hide Your Relations in a Social Network.pdf │ │ ├── Attacking Similarity-Based Link Prediction in Social Networks.pdf │ │ ├── Data Poisoning Attack against Unsupervised Node Embedding Methods.pdf │ │ ├── Fake Node Attacks on Graph Convolutional Networks.pdf │ │ ├── Fast Gradient Attack on Network Embedding.pdf │ │ └── Hiding Individuals and Communities in a Social Network.pdf │ ├── 2019 │ │ ├── A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning.pdf │ │ ├── Adversarial Attacks on Graph Neural Networks via Meta Learning.pdf │ │ ├── Adversarial Attacks on Node Embeddings via Graph Poisoning.pdf │ │ ├── Adversarial Examples on Graph Data Deep Insights into Attack and Defense.pdf │ │ ├── Attacking Graph Convolutional Networks via Rewiring.pdf │ │ ├── Attacking Graph-based Classification via Manipulating the Graph Structure.pdf │ │ ├── Data Poisoning Attack against Knowledge Graph Embedding.pdf │ │ ├── GA Based Q-Attack on Community Detection.pdf │ │ ├── Generalizable Adversarial Attacks with Latent Variable Perturbation Modeling.pdf │ │ ├── Multiscale Evolutionary Perturbation Attack on Community Detection.pdf │ │ ├── Time-aware Gradient Attack on Dynamic Network Link Prediction.pdf │ │ ├── Topology Attack and Defense for Graph Neural Networks An Optimization Perspective.pdf │ │ ├── Unsupervised Euclidean Distance Attack on Network Embedding.pdf │ │ ├── Vertex Nomination, Consistent Estimation, and Adversarial Modification.pdf │ │ └── αCyber Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model.pdf │ └── 2020 │ ├── A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models.pdf │ ├── Adversarial Attack on Community Detection by Hiding Individuals.pdf │ ├── Adversarial Attack on Hierarchical Graph Pooling Neural Networks.pdf │ ├── Adversarial Attacks on Graph Neural Networks Perturbations and their Patterns.pdf │ ├── Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks.pdf │ ├── Adversarial Attacks to Scale-Free Networks Testing the Robustness of Physical Criteria.pdf │ ├── Adversarial Perturbations of Opinion Dynamics in Networks.pdf │ ├── An Adversarial Approach for the Robust Classification of Pneumonia from Chest Radiographs.pdf │ ├── Backdoor Attacks to Graph Neural Networks.pdf │ ├── Black-Box Adversarial Attacks on Graph Neural Networks with Limited Node Access.pdf │ ├── Graph Backdoor.pdf │ ├── Graph Universal Adversarial Attacks A Few Bad Actors Ruin Graph Learning Models.pdf │ ├── Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks.pdf │ ├── Link Prediction Adversarial Attack via Iterative Gradient Attack.pdf │ ├── MGA Momentum Gradient Attack on Network.pdf │ ├── Manipulating Node Similarity Measures in Networks.pdf │ ├── Network disruption maximizing disagreement and polarization in social networks.pdf │ ├── Non-target-specific Node Injection Attacks on Graph Neural Networks A Hierarchical Reinforcement Learning Approach.pdf │ ├── Practical Adversarial Attacks on Graph Neural Networks.pdf │ ├── Scalable Attack on Graph Data by Injecting Vicious Nodes.pdf │ └── Stealing Links from Graph Neural Networks.pdf ├── Defense │ ├── 2017 │ │ └── Adversarial Sets for Regularising Neural Link Predictors.pdf │ ├── 2018 │ │ └── Adversarial Personalized Ranking for Recommendation.pdf │ ├── 2019 │ │ ├── Adversarial Defense Framework for Graph Neural Network.pdf │ │ ├── Adversarial Embedding A robust and elusive Steganography and Watermarking technique.pdf │ │ ├── Adversarial Examples on Graph Data Deep Insights into Attack and Defense.pdf │ │ ├── Adversarial Robustness of Similarity-Based Link Prediction.pdf │ │ ├── Batch Virtual Adversarial Training for Graph Convolutional Networks.pdf │ │ ├── Can Adversarial Network Attack be Defended.pdf │ │ ├── Certifiable Robustness and Robust Training for Graph Convolutional Networks.pdf │ │ ├── Certifiable Robustness to Graph Perturbations.pdf │ │ ├── Characterizing Malicious Edges targeting on Graph Neural Networks.pdf │ │ ├── Comparing and Detecting Adversarial Attacks for Graph Deep Learning.pdf │ │ ├── Edge Dithering for Robust Adaptive Graph Convolutional Networks.pdf │ │ ├── Examining Adversarial Learning against Graph-based IoT Malware Detection Systems.pdf │ │ ├── Graph Adversarial Training Dynamically Regularizing Based on Graph Structure.pdf │ │ ├── Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning.pdf │ │ ├── GraphDefense Towards Robust Graph Convolutional Networks.pdf │ │ ├── GraphSAC Detecting anomalies in large-scale graphs.pdf │ │ ├── Improving Robustness to Attacks Against Vertex Classification.pdf │ │ ├── Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications.pdf │ │ ├── Latent Adversarial Training of Graph Convolution Networks.pdf │ │ ├── Robust Graph Convolutional Networks Against Adversarial Attacks.pdf │ │ ├── Topology Attack and Defense for Graph Neural Networks An Optimization Perspective.pdf │ │ ├── Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings.pdf │ │ ├── Virtual Adversarial Training on Graph Convolutional Networks in Node Classification.pdf │ │ └── αCyber Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model.pdf │ └── 2020 │ ├── Abstract Interpretation based Robustness Certification for Graph Convolutional Networks.pdf │ ├── Adversarial Immunization for Improving Certifiable Robustness on Graphs.pdf │ ├── Adversarial Perturbations of Opinion Dynamics in Networks.pdf │ ├── All You Need Is Low (Rank) Defending Against Adversarial Attacks on Graphs.pdf │ ├── Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing.pdf │ ├── DefenseVGAE Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder.pdf │ ├── Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning.pdf │ ├── Evaluating Graph Vulnerability and Robustness using TIGER.pdf │ ├── Friend or Faux Graph-Based Early Detection of Fake Accounts.pdf │ ├── GNNGUARD Defending Graph Neural Networks against Adversarial Attacks.pdf │ ├── Graph Structure Learning for Robust Graph Neural Networks.pdf │ ├── How Robust Are Graph Neural Networks to Structural Noise.pdf │ ├── Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning.pdf │ ├── On The Stability of Polynomial Spectral Graph Filters.pdf │ ├── On the Robustness of Cascade Diffusion under Node Attacks.pdf │ ├── Power up! Robust Graph Convolutional Network against Evasion Attacks based on Graph Powering.pdf │ ├── Robust Collective Classification against Structural Attacks.pdf │ ├── Robust Graph Learning From Noisy Data.pdf │ ├── Robust Spammer Detection by Nash Reinforcement Learning.pdf │ ├── Robust Training of Graph Convolutional Networks via Latent Perturbation.pdf │ ├── Tensor Graph Convolutional Networks for Multi-relational and Robust Learning.pdf │ ├── Topological Effects on Attacks Against Vertex Classification.pdf │ ├── Towards an Efficient and General Framework of Robust Training for Graph Neural Networks.pdf │ └── Transferring Robustness for Graph Neural Network Against Poisoning Attacks.pdf └── Survey ├── A Survey of Adversarial Learning on Graph.pdf ├── Adversarial Attack and Defense on Graph Data A Survey.pdf ├── Adversarial Attacks and Defenses in Images, Graphs and Text A Review.pdf └── Adversarial Attacks and Defenses on Graphs A Review and Empirical Study.pdf