alphabet.md
November 7, 2023 · View on GitHub
| Title | Type | Venue | Code | Year | |
|---|---|---|---|---|---|
| 0 | (Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More | ðCertification | ðNeurIPS'2023 | :octocat:Code | 2023 |
| 1 | A Comparative Study on Robust Graph Neural Networks to Structural Noises | ðSurvey | ðAAAI DLG'2022 | 2022 | |
| 2 | A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability | ðSurvey | ðarXiv'2022 | 2022 | |
| 3 | A Feature-Importance-Aware and Robust Aggregator for GCN | ð¡Defense | ðCIKM | :octocat:Code | 2020 |
| 4 | A Graph Matching Attack on Privacy-Preserving Record Linkage | âAttack | ðCIKM | 2020 | |
| 5 | A Hard Label Black-box Adversarial Attack Against Graph Neural Networks | âAttack | ðCCS | 2021 | |
| 6 | A Lightweight Metric Defence Strategy for Graph Neural Networks Against Poisoning Attacks | ð¡Defense | ðICICS | :octocat:Code | 2021 |
| 7 | A Novel Defending Scheme for Graph-Based Classification Against Graph Structure Manipulating Attack | ð¡Defense | ðSocialSec | 2020 | |
| 8 | A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models | âAttack | ðAAAI | :octocat:Code | 2020 |
| 9 | A Robust and Generalized Framework for Adversarial Graph Embedding | ð¡Defense | ðarXiv | :octocat:Code | 2021 |
| 10 | A Survey of Adversarial Learning on Graph | ðSurvey | ðarXiv'2020 | 2020 | |
| 11 | A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection | ðSurvey | ðarXiv'2022 | 2022 | |
| 12 | A Systematic Evaluation of Node Embedding Robustness | ðOthers | ðLoGâ2022 | :octocat:Code | 2022 |
| 13 | A Targeted Universal Attack on Graph Convolutional Network | âAttack | ðarXiv | :octocat:Code | 2020 |
| 14 | A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning | âAttack | ðNeurIPS | :octocat:Code | 2019 |
| 15 | A semantic backdoor attack against Graph Convolutional Networks | âAttack | ðarXiv | 2023 | |
| 16 | AANE: Anomaly Aware Network Embedding For Anomalous Link Detection | ð¡Defense | ðICDM | 2020 | |
| 17 | AN-GCN: An Anonymous Graph Convolutional Network Against Edge-Perturbing Attacks | ð¡Defense | ðIEEE TNNLS | 2022 | |
| 18 | ARIEL: Adversarial Graph Contrastive Learning | ð¡Defense | ðarXiv*· | 2022 | |
| 19 | ASGNN: Graph Neural Networks with Adaptive Structure | ð¡Defense | ðICLR OpenReview | 2023 | |
| 20 | Abstract Interpretation based Robustness Certification for Graph Convolutional Networks | ðCertification | ðECAI'2020 | 2020 | |
| 21 | Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications | âAttack | ðICDM | :octocat:Code | 2021 |
| 22 | Adaptive Adversarial Attack on Graph Embedding via GAN | âAttack | ðSocialSec | 2020 | |
| 23 | AdverSparse: An Adversarial Attack Framework for Deep Spatial-Temporal Graph Neural Networks | âAttack | ðICASSP | 2022 | |
| 24 | Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge | âAttack | ðarXiv | 2021 | |
| 25 | Adversarial Attack against Cross-lingual Knowledge Graph Alignment | âAttack | ðEMNLP | 2021 | |
| 26 | Adversarial Attack and Defense on Graph Data: A Survey | ðSurvey | ðarXiv'2018 | 2018 | |
| 27 | Adversarial Attack on Community Detection by Hiding Individuals | âAttack | ðWWW | :octocat:Code | 2020 |
| 28 | Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem | âAttack | ðWSDM | :octocat:Code | 2022 |
| 29 | Adversarial Attack on Graph Structured Data | âAttack | ðICML | :octocat:Code | 2018 |
| 30 | Adversarial Attack on Hierarchical Graph Pooling Neural Networks | âAttack | ðarXiv | 2020 | |
| 31 | Adversarial Attack on Large Scale Graph | âAttack | ðTKDE | :octocat:Code | 2021 |
| 32 | Adversarial Attacks and Defenses in Images, Graphs and Text: A Review | ðSurvey | ðarXiv'2019 | 2019 | |
| 33 | Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies | ðSurvey | ðSIGKDD Explorations'2021 | 2021 | |
| 34 | Adversarial Attacks on Deep Graph Matching | âAttack | ðNeurIPS | 2020 | |
| 35 | Adversarial Attacks on Graph Classification via Bayesian Optimisation | âAttack | ðNeurIPS | :octocat:Code | 2021 |
| 36 | Adversarial Attacks on Graph Neural Networks via Meta Learning | âAttack | ðICLR | :octocat:Code | 2019 |
| 37 | Adversarial Attacks on Graph Neural Networks via Node Injections: A Hierarchical Reinforcement Learning Approach | âAttack | ðWWW | 2020 | |
| 38 | Adversarial Attacks on Graph Neural Networks: Perturbations and their Patterns | âAttack | ðTKDD | 2020 | |
| 39 | Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods | âAttack | ðEMNLP | :octocat:Code | 2021 |
| 40 | Adversarial Attacks on Link Prediction Algorithms Based on Graph Neural Networks | âAttack | ðAsia CCS | 2020 | |
| 41 | Adversarial Attacks on Neural Networks for Graph Data | âAttack | ðKDD | :octocat:Code | 2018 |
| 42 | Adversarial Attacks on Node Embeddings via Graph Poisoning | âAttack | ðICML | :octocat:Code | 2019 |
| 43 | Adversarial Attacks to Scale-Free Networks: Testing the Robustness of Physical Criteria | âAttack | ðarXiv | 2020 | |
| 44 | Adversarial Camouflage for Node Injection Attack on Graphs | âAttack | ðarXiv | 2022 | |
| 45 | Adversarial Defense Framework for Graph Neural Network | ð¡Defense | ðarXiv | 2019 | |
| 46 | Adversarial Detection on Graph Structured Data | ð¡Defense | ðPPMLP | 2020 | |
| 47 | Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models | âAttack | ðarXiv | :octocat:Code | 2021 |
| 48 | Adversarial Embedding: A robust and elusive Steganography and Watermarking technique | ð¡Defense | ðarXiv | 2019 | |
| 49 | Adversarial Examples on Graph Data: Deep Insights into Attack and Defense | âAttack | ðIJCAI | :octocat:Code | 2019 |
| 50 | Adversarial Immunization for Improving Certifiable Robustness on Graphs | ðCertification | ðWSDM'2021 | 2021 | |
| 51 | Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks | âAttack | ðICDM | :octocat:Code | 2022 |
| 52 | Adversarial Label Poisoning Attack on Graph Neural Networks via Label Propagation | âAttack | ðECCV | 2022 | |
| 53 | Adversarial Label-Flipping Attack and Defense for Graph Neural Networks | âAttack | ðICDM | :octocat:Code | 2020 |
| 54 | Adversarial Personalized Ranking for Recommendation | ð¡Defense | ðSIGIR | :octocat:Code | 2018 |
| 55 | Adversarial Perturbations of Opinion Dynamics in Networks | âAttack | ðarXiv | 2020 | |
| 56 | Adversarial Privacy Preserving Graph Embedding against Inference Attack | ð¡Defense | ðarXiv | :octocat:Code | 2020 |
| 57 | Adversarial Robustness of Graph-based Anomaly Detection | âAttack | ðarXiv | 2022 | |
| 58 | Adversarial Robustness of Probabilistic Network Embedding for Link Prediction | ð¡Defense | ðarXiv | 2021 | |
| 59 | Adversarial Robustness of Similarity-Based Link Prediction | ð¡Defense | ðICDM | 2019 | |
| 60 | Adversarial Sets for Regularising Neural Link Predictors | âAttack | ðUAI | :octocat:Code | 2017 |
| 61 | Adversarial Training Methods for Network Embedding | ð¡Defense | ðWWW | :octocat:Code | 2019 |
| 62 | Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions | ð¡Defense | ðNeurIPS | :octocat:Code | 2023 |
| 63 | Adversarial attack on BC classification for scale-free networks | âAttack | ðAIP Chaos | 2020 | |
| 64 | Adversarial for Social Privacy: A Poisoning Strategy to Degrade User Identity Linkage | âAttack | ðarXiv | 2022 | |
| 65 | Adversary for Social Good: Leveraging Attribute-Obfuscating Attack to Protect User Privacy on Social Networks | âAttack | ðSecureComm | 2022 | |
| 66 | Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks | ð¡Defense | ðAAAI | 2020 | |
| 67 | All You Need Is Low (Rank): Defending Against Adversarial Attacks on Graphs | ð¡Defense | ðWSDM | :octocat:Code | 2020 |
| 68 | An Efficient Adversarial Attack on Graph Structured Data | âAttack | ðIJCAI Workshop | 2020 | |
| 69 | An Introduction to Robust Graph Convolutional Networks | ð¡Defense | ðarXiv | 2021 | |
| 70 | Anti-perturbation of Online Social Networks by Graph Label Transition | ð¡Defense | ðarXiv | 2020 | |
| 71 | Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond | ð¡Defense | ðCVPR | :octocat:Code | 2022 |
| 72 | Are Defenses for Graph Neural Networks Robust? | âAttack | ðNeurIPS | :octocat:Code | 2022 |
| 73 | Are Gradients on Graph Structure Reliable in Gray-box Attacks? | âAttack | ðCIKM | :octocat:Code | 2022 |
| 74 | Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Network | âAttack | ðarXiv | 2018 | |
| 75 | Attackability Characterization of Adversarial Evasion Attack on Discrete Data | âAttack | ðKDD | 2020 | |
| 76 | Attacking Graph Convolutional Networks via Rewiring | âAttack | ðarXiv | 2019 | |
| 77 | Attacking Graph Neural Networks at Scale | âAttack | ðAAAI workshop | 2021 | |
| 78 | Attacking Graph-Based Classification without Changing Existing Connections | âAttack | ðACSAC | 2020 | |
| 79 | Attacking Graph-based Classification via Manipulating the Graph Structure | âAttack | ðCCS | 2019 | |
| 80 | Attacking Similarity-Based Link Prediction in Social Networks | âAttack | ðAAMAS | 2018 | |
| 81 | Backdoor Attacks to Graph Neural Networks | âAttack | ðSACMAT | :octocat:Code | 2020 |
| 82 | Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees | âAttack | ðCVPR | :octocat:Code | 2022 |
| 83 | Batch Virtual Adversarial Training for Graph Convolutional Networks | ð¡Defense | ðICML | :octocat:Code | 2019 |
| 84 | Bayesian Robust Graph Contrastive Learning | ð¡Defense | ðarXiv | :octocat:Code | 2022 |
| 85 | Bayesian graph convolutional neural networks for semi-supervised classification | ð¡Defense | ðAAAI | :octocat:Code | 2019 |
| 86 | BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection | âAttack | ðICDM | :octocat:Code | 2022 |
| 87 | Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense | âAttack | ðarXiv | 2021 | |
| 88 | Black-box Node Injection Attack for Graph Neural Networks | âAttack | ðarXiv | :octocat:Code | 2022 |
| 89 | Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs | âAttack | ðAAAI | :octocat:Code | 2022 |
| 90 | CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks | ðOthers | ðarXiv'2021 | 2021 | |
| 91 | COREATTACK: Breaking Up the Core Structure of Graphs | âAttack | ðarXiv | 2021 | |
| 92 | Camouflaged Poisoning Attack on Graph Neural Networks | âAttack | ðICDM | 2022 | |
| 93 | Can Adversarial Network Attack be Defended? | ð¡Defense | ðarXiv | 2019 | |
| 94 | Certifiable Robustness and Robust Training for Graph Convolutional Networks | ðCertification | ðKDD'2019 | :octocat:Code | 2019 |
| 95 | Certifiable Robustness of Graph Convolutional Networks under Structure Perturbation | ðCertification | ðKDD'2020 | :octocat:Code | 2020 |
| 96 | Certifiable Robustness to Graph Perturbations | ðCertification | ðNeurIPS'2019 | :octocat:Code | 2019 |
| 97 | Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing | ðCertification | ðWWW'2020 | 2020 | |
| 98 | Certified Robustness of Graph Classification against Topology Attack with Randomized Smoothing | ðCertification | ðGLOBECOM'2020 | 2020 | |
| 99 | Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks | ðCertification | ðNeurIPS'2020 | :octocat:Code | 2020 |
| 100 | Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation | ðCertification | ðKDD'2021 | :octocat:Code | 2021 |
| 101 | Certifying Robustness of Graph Laplacian Based Semi-Supervised Learning | ðCertification | ðICLR OpenReview'2021 | 2021 | |
| 102 | Characterizing Malicious Edges targeting on Graph Neural Networks | ð¡Defense | ðICLR OpenReview | :octocat:Code | 2019 |
| 103 | Cluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors | âAttack | ðIJCAI | :octocat:Code | 2022 |
| 104 | CoG: a Two-View Co-training Framework for Defending Adversarial Attacks on Graph | ð¡Defense | ðarXiv | 2021 | |
| 105 | Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks | ðCertification | ðICLR'2021 | :octocat:Code | 2021 |
| 106 | Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian | ð¡Defense | ðNeurIPS | 2020 | |
| 107 | Comparing and Detecting Adversarial Attacks for Graph Deep Learning | ð¡Defense | ðRLGM@ICLR | 2019 | |
| 108 | Cross Entropy Attack on Deep Graph Infomax | âAttack | ðIEEE ISCAS | 2020 | |
| 109 | Data Poisoning Attack against Knowledge Graph Embedding | âAttack | ðIJCAI | 2019 | |
| 110 | Data Poisoning Attack against Unsupervised Node Embedding Methods | âAttack | ðarXiv | 2018 | |
| 111 | DeHiB: Deep Hidden Backdoor Attack on Semi-Supervised Learning via Adversarial Perturbation | âAttack | ðAAAI | 2021 | |
| 112 | Dealing with the unevenness: deeper insights in graph-based attack and defense | âAttack | ðMachine Learning | 2022 | |
| 113 | Deep Graph Structure Learning for Robust Representations: A Survey | ðSurvey | ðarXiv'2021 | 2021 | |
| 114 | Deep Learning on Graphs: A Survey | ðSurvey | ðarXiv'2018 | 2018 | |
| 115 | DeepInsight: Interpretability Assisting Detection of Adversarial Samples on Graphs | ð¡Defense | ðECML | 2021 | |
| 116 | DeepRobust: a Platform for Adversarial Attacks and Defenses | âToolbox | ðAAAIâ2021 | :octocat:DeepRobust | 2021 |
| 117 | Defending Against Backdoor Attack on Graph Nerual Network by Explainability | ð¡Defense | ðarXiv | 2022 | |
| 118 | Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision | ð¡Defense | ðAAAI | :octocat:Code | 2022 |
| 119 | DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder | ð¡Defense | ðarXiv | :octocat:Code | 2020 |
| 120 | Derivative-free optimization adversarial attacks for graph convolutional networks | âAttack | ðPeerJ | 2021 | |
| 121 | Detecting Topology Attacks against Graph Neural Networks | ð¡Defense | ðarXiv | 2022 | |
| 122 | Detection and Defense of Topological Adversarial Attacks on Graphs | ð¡Defense | ðAISTATS | 2021 | |
| 123 | Distributionally Robust Semi-Supervised Learning Over Graphs | ð¡Defense | ðICLR | 2021 | |
| 124 | Dynamic Knowledge Graph-based Dialogue Generation with Improved Adversarial Meta-Learning | ð¡Defense | ðarXiv | 2020 | |
| 125 | E-GraphSAGE: A Graph Neural Network based Intrusion Detection System | ð¡Defense | ðarXiv | 2021 | |
| 126 | EGC2: Enhanced Graph Classification with Easy Graph Compression | ð¡Defense | ðarXiv | 2021 | |
| 127 | Edge Dithering for Robust Adaptive Graph Convolutional Networks | ð¡Defense | ðarXiv | 2019 | |
| 128 | Efficient Evasion Attacks to Graph Neural Networks via Influence Function | âAttack | ðarXiv | 2020 | |
| 129 | Efficient Robustness Certificates for Discrete Data: Sparsity - Aware Randomized Smoothing for Graphs, Images and More | ðCertification | ðICML'2020 | :octocat:Code | 2020 |
| 130 | Elastic Graph Neural Networks | ð¡Defense | ðICML | :octocat:Code | 2021 |
| 131 | Empowering Graph Representation Learning with Test-Time Graph Transformation | ð¡Defense | ðICLR | :octocat:Code | 2023 |
| 132 | Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters | ð¡Defense | ðCIKM | :octocat:Code | 2020 |
| 133 | Enhancing Robustness and Resilience of Multiplex Networks Against Node-Community Cascading Failures | ð¡Defense | ðIEEE TSMC | 2021 | |
| 134 | Evaluating Graph Vulnerability and Robustness using TIGER | âToolbox | ðarXivâ2021 | :octocat:TIGER | 2021 |
| 135 | Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts | ðOthers | ðarXivâ2023 | :octocat:Code | 2023 |
| 136 | EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks | ð¡Defense | ðarXiv | 2022 | |
| 137 | Examining Adversarial Learning against Graph-based IoT Malware Detection Systems | ð¡Defense | ðarXiv | 2019 | |
| 138 | Explainability-based Backdoor Attacks Against Graph Neural Networks | âAttack | ðWiseML@WiSec | 2021 | |
| 139 | Exploratory Adversarial Attacks on Graph Neural Networks | âAttack | ðICDM | :octocat:Code | 2020 |
| 140 | Exploratory Adversarial Attacks on Graph Neural Networks for Semi-Supervised Node Classification | âAttack | ðPattern Recognition | 2022 | |
| 141 | Exploring High-Order Structure for Robust Graph Structure Learning | ð¡Defense | ðarXiv | 2022 | |
| 142 | Expressive 1-Lipschitz Neural Networks for Robust Multiple Graph Learning against Adversarial Attacks | ð¡Defense | ðICML | 2021 | |
| 143 | FHA: Fast Heuristic Attack Against Graph Convolutional Networks | âAttack | ðICDS | 2021 | |
| 144 | FLAG: Adversarial Data Augmentation for Graph Neural Networks | ðOthers | ðarXiv'2020 | :octocat:Code | 2020 |
| 145 | Fake Node Attacks on Graph Convolutional Networks | âAttack | ðarXiv | 2018 | |
| 146 | Fast Gradient Attack on Network Embedding | âAttack | ðarXiv | 2018 | |
| 147 | FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification | ð¡Defense | ðarXiv | 2022 | |
| 148 | Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks | ð¡Defense | ðWWW | 2020 | |
| 149 | GA Based Q-Attack on Community Detection | âAttack | ðTCSS | 2019 | |
| 150 | GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injections | âAttack | ðarXiv | :octocat:Code | 2022 |
| 151 | GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation | âAttack | ðarXiv | 2022 | |
| 152 | GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks | ð¡Defense | ðarXiv | 2022 | |
| 153 | GNNGuard: Defending Graph Neural Networks against Adversarial Attacks | ð¡Defense | ðNeurIPS | :octocat:Code | 2020 |
| 154 | GNNUnlock: Graph Neural Networks-based Oracle-less Unlocking Scheme for Provably Secure Logic Locking | âAttack | ðDATE Conference | 2021 | |
| 155 | GReady for Emerging Threats to Recommender Systems? A Graph Convolution-based Generative Shilling Attack | âAttack | ðInformation Sciences | 2021 | |
| 156 | GUAP: Graph Universal Attack Through Adversarial Patching | âAttack | ðarXiv | :octocat:Code | 2023 |
| 157 | GUARD: Graph Universal Adversarial Defense | ð¡Defense | ðarXiv | :octocat:Code | 2022 |
| 158 | Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling | âAttack | ðarXiv | 2019 | |
| 159 | Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness | âAttack | ðNeurIPS | 2021 | |
| 160 | Graph Adversarial Attack via Rewiring | âAttack | ðKDD | :octocat:Code | 2021 |
| 161 | Graph Adversarial Immunization for Certifiable Robustness | ðCertification | ðarXiv'2023 | 2023 | |
| 162 | Graph Adversarial Networks: Protecting Information against Adversarial Attacks | ð¡Defense | ðICLR OpenReview | :octocat:Code | 2020 |
| 163 | Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure | ð¡Defense | ðTKDE | :octocat:Code | 2019 |
| 164 | Graph Backdoor | âAttack | ðUSENIX Security | 2021 | |
| 165 | Graph Contrastive Learning with Augmentations | ð¡Defense | ðNeurIPS | :octocat:Code | 2020 |
| 166 | Graph Information Bottleneck | ð¡Defense | ðNeurIPS | :octocat:Code | 2020 |
| 167 | Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning | ð¡Defense | ðarXiv | :octocat:Code | 2019 |
| 168 | Graph Neural Network for Local Corruption Recovery | ð¡Defense | ðarXiv | :octocat:Code | 2022 |
| 169 | Graph Neural Networks Methods, Applications, and Opportunities | ðSurvey | ðarXiv'2021 | 2021 | |
| 170 | Graph Neural Networks Taxonomy, Advances and Trends | ðSurvey | ðarXiv'2020 | 2020 | |
| 171 | Graph Neural Networks with Adaptive Residual | ð¡Defense | ðNeurIPS | :octocat:Code | 2021 |
| 172 | Graph Neural Networks with Feature and Structure Aware Random Walk | ð¡Defense | ðarXiv | 2021 | |
| 173 | Graph Neural Networks: Architectures, Stability and Transferability | âStability | ðarXiv'2020 | 2020 | |
| 174 | Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification | ð¡Defense | ðNeurIPS | :octocat:Code | 2021 |
| 175 | Graph Random Neural Networks for Semi-Supervised Learning on Graphs | ð¡Defense | ðNeurIPS | :octocat:Code | 2020 |
| 176 | Graph Robustness Benchmark: Rethinking and Benchmarking Adversarial Robustness of Graph Neural Networks | âToolbox | ðNeurIPS'2021 | :octocat:Graph Robustness Benchmark (GRB) | 2021 |
| 177 | Graph Sanitation with Application to Node Classification | ð¡Defense | ðarXiv | 2021 | |
| 178 | Graph Stochastic Neural Networks for Semi-supervised Learning | âAttack | ðarXiv | :octocat:Code | 2021 |
| 179 | Graph Structural Attack by Perturbing Spectral Distance | âAttack | ðKDD | 2022 | |
| 180 | Graph Structure Learning for Robust Graph Neural Networks | ð¡Defense | ðKDD | :octocat:Code | 2020 |
| 181 | Graph Structure Reshaping Against Adversarial Attacks on Graph Neural Networks | ð¡Defense | ðNone | :octocat:Code | 2020 |
| 182 | Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation | ð¡Defense | ðarXiv | 2021 | |
| 183 | Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models | âAttack | ðIJCAI | :octocat:Code | 2021 |
| 184 | Graph Vulnerability and Robustness: A Survey | ðSurvey | ðTKDE'2022 | 2022 | |
| 185 | Graph and Graphon Neural Network Stability | âStability | ðarXiv'2020 | 2020 | |
| 186 | Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learning | âAttack | ðarXiv | 2021 | |
| 187 | Graph-Revised Convolutional Network | ð¡Defense | ðECML-PKDD | :octocat:Code | 2020 |
| 188 | Graph-based Adversarial Online Kernel Learning with Adaptive Embedding | ð¡Defense | ðICDM | 2021 | |
| 189 | GraphAttacker: A General Multi-Task GraphAttack Framework | âAttack | ðarXiv | :octocat:Code | 2021 |
| 190 | GraphDefense: Towards Robust Graph Convolutional Networks | ð¡Defense | ðarXiv | 2019 | |
| 191 | GraphMI: Extracting Private Graph Data from Graph Neural Networks | âAttack | ðIJCAI | :octocat:Code | 2021 |
| 192 | GraphSAC: Detecting anomalies in large-scale graphs | ð¡Defense | ðarXiv | 2019 | |
| 193 | Graphfool: Targeted Label Adversarial Attack on Graph Embedding | âAttack | ðarXiv | 2021 | |
| 194 | GreatX: A graph reliability toolbox based on PyTorch and PyTorch Geometric | âToolbox | ðarXivâ2022 | :octocat:GreatX | 2022 |
| 195 | Hiding Individuals and Communities in a Social Network | âAttack | ðNature Human Behavior | 2018 | |
| 196 | Hierarchical Randomized Smoothing | ðCertification | ðNeurIPS'2023 | :octocat:Code | 2023 |
| 197 | How Does Bayesian Noisy Self-Supervision Defend Graph Convolutional Networks? | ð¡Defense | ðNeural Processing Letters | 2022 | |
| 198 | How Members of Covert Networks Conceal the Identities of Their Leaders | âAttack | ðACM TIST | 2021 | |
| 199 | How Robust Are Graph Neural Networks to Structural Noise? | ð¡Defense | ðDLGMA | 2020 | |
| 200 | How does Heterophily Impact Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications | ð¡Defense | ðKDD | :octocat:Code | 2022 |
| 201 | How effective are Graph Neural Networks in Fraud Detection for Network Data? | ð¡Defense | ðarXiv | 2021 | |
| 202 | I-GCN: Robust Graph Convolutional Network via Influence Mechanism | ð¡Defense | ðarXiv | 2020 | |
| 203 | Imperceptible Adversarial Attacks on Discrete-Time Dynamic Graph Models | âAttack | ðNeurIPS | 2022 | |
| 204 | Improving Robustness of Graph Neural Networks with Heterophily-Inspired Designs | ð¡Defense | ðarXiv | 2021 | |
| 205 | Improving Robustness to Attacks Against Vertex Classification | ð¡Defense | ðMLG@KDD | 2019 | |
| 206 | Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning | ðCertification | ðAAAI'2020 | 2020 | |
| 207 | Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networks | âAttack | ðBigData | 2020 | |
| 208 | Inference Attacks Against Graph Neural Networks | âAttack | ðUSENIX Security | :octocat:Code | 2022 |
| 209 | Information Obfuscation of Graph Neural Network | ð¡Defense | ðICML | :octocat:Code | 2021 |
| 210 | Integrated Defense for Resilient Graph Matching | ð¡Defense | ðICML | 2021 | |
| 211 | Interpretable Stability Bounds for Spectral Graph Filters | ð¡Defense | ðarXiv | 2021 | |
| 212 | Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection | âAttack | ðarXiv | 2022 | |
| 213 | Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications | ð¡Defense | ðNAACL | :octocat:Code | 2019 |
| 214 | IoT-based Android Malware Detection Using Graph Neural Network With Adversarial Defense | ð¡Defense | ðIEEE IOT | 2022 | |
| 215 | Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings | âAttack | ðarXiv | :octocat:Code | 2021 |
| 216 | Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids using Graph Neural Networks | âAttack | ðarXiv | 2021 | |
| 217 | Jointly Attacking Graph Neural Network and its Explanations | âAttack | ðarXiv | 2021 | |
| 218 | LOKI: A Practical Data Poisoning Attack Framework against Next Item Recommendations | âAttack | ðTKDE | 2022 | |
| 219 | LPGNet: Link Private Graph Networks for Node Classification | ð¡Defense | ðarXiv | 2022 | |
| 220 | Label specificity attack: Change your label as I want | âAttack | ðIJIS | 2022 | |
| 221 | Label-Only Membership Inference Attack against Node-Level Graph Neural NetworksCluster Attack: Query-based Adversarial Attacks on Graphs with Graph-Dependent Priors | âAttack | ðarXiv | 2022 | |
| 222 | Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks | ð¡Defense | ðarXiv | 2022 | |
| 223 | Latent Adversarial Training of Graph Convolution Networks | ð¡Defense | ðLRGSD@ICML | :octocat:Code | 2019 |
| 224 | Learning Graph Embedding with Adversarial Training Methods | ð¡Defense | ðIEEE Transactions on Cybernetics | 2020 | |
| 225 | Learning Robust Representation through Graph Adversarial Contrastive Learning | ð¡Defense | ðarXiv | 2022 | |
| 226 | Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation | âAttack | ðICLR | :octocat:Code | 2020 |
| 227 | Learning to Drop: Robust Graph Neural Network via Topological Denoising | ð¡Defense | ðWSDM | :octocat:Code | 2021 |
| 228 | Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning | âAttack | ðAAAI | :octocat:Code | 2023 |
| 229 | Link Prediction Adversarial Attack Via Iterative Gradient Attack | âAttack | ðIEEE Trans | 2020 | |
| 230 | Link-Backdoor: Backdoor Attack on Link Prediction via Node Injection | âAttack | ðarXiv | :octocat:Code | 2022 |
| 231 | LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis | ð¡Defense | ðarXiv | 2021 | |
| 232 | Localized Randomized Smoothing for Collective Robustness Certification | ðCertification | ðICLR'2023 | 2023 | |
| 233 | MGA: Momentum Gradient Attack on Network | âAttack | ðarXiv | 2020 | |
| 234 | Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights | ð¡Defense | ðarXiv | 2021 | |
| 235 | Manipulating Node Similarity Measures in Networks | âAttack | ðAAMAS | 2020 | |
| 236 | Membership Inference Attack on Graph Neural Networks | âAttack | ðarXiv | 2021 | |
| 237 | Membership Inference Attacks Against Robust Graph Neural Network | âAttack | ðCSS | 2022 | |
| 238 | Mind Your Solver! On Adversarial Attack and Defense for Combinatorial Optimization | ð¡Defense | ðarXiv | :octocat:Code | 2022 |
| 239 | Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization | âAttack | ðAsia CCS | :octocat:Code | 2022 |
| 240 | Model Inversion Attacks against Graph Neural Networks | âAttack | ðTKDE | 2022 | |
| 241 | Model Stealing Attacks Against Inductive Graph Neural Networks | âAttack | ðIEEE Symposium on Security and Privacy | :octocat:Code | 2022 |
| 242 | More is Better (Mostly): On the Backdoor Attacks in Federated Graph Neural Networks | âAttack | ðarXiv | 2022 | |
| 243 | Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifs | âAttack | ðarXiv | 2022 | |
| 244 | Multiscale Evolutionary Perturbation Attack on Community Detection | âAttack | ðarXiv | 2019 | |
| 245 | NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs | ð¡Defense | ðarXiv | 2022 | |
| 246 | Near-Black-Box Adversarial Attacks on Graph Neural Networks as An Influence Maximization Problem | âAttack | ðICLR OpenReview | 2020 | |
| 247 | Neighboring Backdoor Attacks on Graph Convolutional Network | âAttack | ðarXiv | :octocat:Code | 2022 |
| 248 | NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data | ð¡Defense | ðTKDE | :octocat:Code | 2021 |
| 249 | Network Embedding Attack: An Euclidean Distance Based Method | âAttack | ðMDATA | 2021 | |
| 250 | Network Structural Vulnerability A Multi-Objective Attacker Perspective | âAttack | ðIEEE Trans | 2019 | |
| 251 | Network disruption: maximizing disagreement and polarization in social networks | âAttack | ðarXiv | :octocat:Code | 2020 |
| 252 | Node Copying for Protection Against Graph Neural Network Topology Attacks | ð¡Defense | ðarXiv | 2020 | |
| 253 | Node Feature Kernels Increase Graph Convolutional Network Robustness | ð¡Defense | ðarXiv | :octocat:Code | 2021 |
| 254 | Node Injection for Class-specific Network Poisoning | âAttack | ðarXiv | :octocat:Code | 2023 |
| 255 | Node Similarity Preserving Graph Convolutional Networks | ð¡Defense | ðWSDM | :octocat:Code | 2021 |
| 256 | Node-Level Membership Inference Attacks Against Graph Neural Networks | âAttack | ðarXiv | 2021 | |
| 257 | Not All Low-Pass Filters are Robust in Graph Convolutional Networks | ð¡Defense | ðNeurIPS | :octocat:Code | 2021 |
| 258 | On Generalization of Graph Autoencoders with Adversarial Training | ð¡Defense | ðECML | 2021 | |
| 259 | On The Stability of Polynomial Spectral Graph Filters | ð¡Defense | ðICASSP | :octocat:Code | 2020 |
| 260 | On the Prediction Instability of Graph Neural Networks | âStability | ðarXiv'2022 | 2022 | |
| 261 | On the Relationship between Heterophily and Robustness of Graph Neural Networks | ð¡Defense | ðarXiv | 2021 | |
| 262 | On the Robustness of Cascade Diffusion under Node Attacks | ð¡Defense | ðWWW | :octocat:Code | 2020 |
| 263 | On the Robustness of Graph Neural Diffusion to Topology Perturbations | ð¡Defense | ðNeurIPS | :octocat:Code | 2022 |
| 264 | On the Stability of Graph Convolutional Neural Networks under Edge Rewiring | âStability | ðarXiv'2020 | 2020 | |
| 265 | On the Vulnerability of Graph Learning based Collaborative Filtering | ð¡Defense | ðTIS | 2022 | |
| 266 | One Vertex Attack on Graph Neural Networks-based Spatiotemporal Forecasting | âAttack | ðICLR OpenReview | 2020 | |
| 267 | Optimal Edge Weight Perturbations to Attack Shortest Paths | âAttack | ðarXiv | 2021 | |
| 268 | PATHATTACK: Attacking Shortest Paths in Complex Networks | âAttack | ðarXiv | 2021 | |
| 269 | PeerNets Exploiting Peer Wisdom Against Adversarial Attacks | âAttack | ðICLR | :octocat:Code | 2019 |
| 270 | Personalized privacy protection in social networks through adversarial modeling | ð¡Defense | ðAAAI | 2021 | |
| 271 | Perturbation Sensitivity of GNNs | ðOthers | ðcs224w'2019 | 2019 | |
| 272 | Poisoning GNN-based Recommender Systems with Generative Surrogate-based Attacks | âAttack | ðACM TIS | 2022 | |
| 273 | Poisoning Knowledge Graph Embeddings via Relation Inference Patterns | âAttack | ðACL | :octocat:Code | 2021 |
| 274 | Power up! Robust Graph Convolutional Network against Evasion Attacks based on Graph Powering | ð¡Defense | ðAAAI | :octocat:Code | 2021 |
| 275 | Practical Adversarial Attacks on Graph Neural Networks | âAttack | ðICML Workshop | 2020 | |
| 276 | Practical Attacks Against Graph-based Clustering | âAttack | ðCCS | 2017 | |
| 277 | Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation | âAttack | ðarXiv | 2021 | |
| 278 | Private Graph Extraction via Feature Explanations | âAttack | ðarXiv | 2022 | |
| 279 | Projective Ranking-based GNN Evasion Attacks | âAttack | ðarXiv | 2022 | |
| 280 | Projective Ranking: A Transferable Evasion Attack Method on Graph Neural Networks | âAttack | ðCIKM | 2021 | |
| 281 | Provable Overlapping Community Detection in Weighted Graphs | ð¡Defense | ðNeurIPS | 2020 | |
| 282 | Provably Robust Node Classification via Low-Pass Message Passing | ð¡Defense | ðICDM | 2020 | |
| 283 | Query-free Black-box Adversarial Attacks on Graphs | âAttack | ðarXiv | 2020 | |
| 284 | Randomized Generation of Adversary-Aware Fake Knowledge Graphs to Combat Intellectual Property Theft | ð¡Defense | ðAAAI | 2021 | |
| 285 | Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks | ðCertification | ðNeurIPS'2022 | :octocat:Code | 2022 |
| 286 | Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack | ðSurvey | ðarXiv'2022 | 2022 | |
| 287 | Reinforcement Learning For Data Poisoning on Graph Neural Networks | âAttack | ðarXiv | 2021 | |
| 288 | Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphs | âAttack | ðarXiv | 2020 | |
| 289 | Releasing Graph Neural Networks with Differential Privacy Guarantees | ð¡Defense | ðarXiv | 2021 | |
| 290 | Reliable Graph Neural Networks via Robust Aggregation | ð¡Defense | ðNeurIPS | :octocat:Code | 2020 |
| 291 | Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN | ð¡Defense | ðKDD | :octocat:Code | 2022 |
| 292 | ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks | ð¡Defense | ðarXiv | 2020 | |
| 293 | Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation | ð¡Defense | ðECML-PKDD | 2022 | |
| 294 | Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification | âAttack | ðarXiv | 2021 | |
| 295 | Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective | âAttack | ðICLR | :octocat:Code | 2023 |
| 296 | Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective | âAttack | ðarXiv | 2022 | |
| 297 | Revisiting Robustness in Graph Machine Learning | ð¡Defense | ðICLR | :octocat:Code | 2023 |
| 298 | Ricci-GNN: Defending Against Structural Attacks Through a Geometric Approach | ð¡Defense | ðICLR OpenReview | 2020 | |
| 299 | RoGAT: a robust GNN combined revised GAT with adjusted graphs | ð¡Defense | ðarXiv | 2020 | |
| 300 | Robust Certification for Laplace Learning on Geometric Graphs | ðCertification | ðMSMLâ2021 | 2021 | |
| 301 | Robust Collective Classification against Structural Attacks | ð¡Defense | ðPreprint | 2020 | |
| 302 | Robust Counterfactual Explanations on Graph Neural Networks | ð¡Defense | ðarXiv | 2021 | |
| 303 | Robust Detection of Adaptive Spammers by Nash Reinforcement Learning | ð¡Defense | ðKDD | :octocat:Code | 2020 |
| 304 | Robust Graph Convolutional Networks Against Adversarial Attacks | ð¡Defense | ðKDD | :octocat:Code | 2019 |
| 305 | Robust Graph Data Learning via Latent Graph Convolutional Representation | ð¡Defense | ðarXiv | 2019 | |
| 306 | Robust Graph Learning From Noisy Data | ð¡Defense | ðIEEE Trans | 2020 | |
| 307 | Robust Graph Learning Under Wasserstein Uncertainty | ð¡Defense | ðarXiv | 2021 | |
| 308 | Robust Graph Neural Networks using Weighted Graph Laplacian | ð¡Defense | ðSPCOM | :octocat:Code | 2022 |
| 309 | Robust Graph Neural Networks via Ensemble Learning | ð¡Defense | ðMathematics | 2022 | |
| 310 | Robust Graph Neural Networks via Probabilistic Lipschitz Constraints | ð¡Defense | ðarXiv | 2021 | |
| 311 | Robust Graph Representation Learning for Local Corruption Recovery | ð¡Defense | ðICML workshop | 2022 | |
| 312 | Robust Graph Representation Learning via Neural Sparsification | ð¡Defense | ðICML | 2020 | |
| 313 | Robust Graph Representation Learning via Predictive Coding | ð¡Defense | ðarXiv | 2022 | |
| 314 | Robust Heterogeneous Graph Neural Networks against Adversarial Attacks | ð¡Defense | ðAAAI | 2022 | |
| 315 | Robust Mid-Pass Filtering Graph Convolutional Networks | ð¡Defense | ðWWW | 2023 | |
| 316 | Robust Network Alignment via Attack Signal Scaling and Adversarial Perturbation Elimination | ð¡Defense | ðWWW | 2021 | |
| 317 | Robust Node Classification on Graphs: Jointly from Bayesian Label Transition and Topology-based Label Propagation | ð¡Defense | ðCIKM | :octocat:Code | 2022 |
| 318 | Robust Tensor Graph Convolutional Networks via T-SVD based Graph Augmentation | ð¡Defense | ðKDD | :octocat:Code | 2022 |
| 319 | Robust Training of Graph Convolutional Networks via Latent Perturbation | ð¡Defense | ðECML-PKDD | 2020 | |
| 320 | Robust Training of Graph Neural Networks via Noise Governance | ð¡Defense | ðWSDM | :octocat:Code | 2023 |
| 321 | Robust cross-network node classification via constrained graph mutual information | ð¡Defense | ðKBS | 2022 | |
| 322 | Robust graph convolutional networks with directional graph adversarial training | ð¡Defense | ðApplied Intelligence | 2021 | |
| 323 | Robustness of Graph Neural Networks at Scale | âAttack | ðNeurIPS | :octocat:Code | 2021 |
| 324 | Robustness of deep learning models on graphs: A survey | ðSurvey | ðAI Open'2021 | 2021 | |
| 325 | SAGE: Intrusion Alert-driven Attack Graph Extractor | âAttack | ðKDD Workshop | :octocat:Code | 2021 |
| 326 | SIGL: Securing Software Installations Through Deep Graph Learning | ðOthers | ðUSENIX'2021 | 2021 | |
| 327 | Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers | âAttack | ðarXiv | 2020 | |
| 328 | Scalable Attack on Graph Data by Injecting Vicious Nodes | âAttack | ðECML-PKDD | :octocat:Code | 2020 |
| 329 | Self-Supervised Graph Structure Refinement for Graph Neural Networks | ð¡Defense | ðWSDM | :octocat:Code | 2023 |
| 330 | Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection | âAttack | ðarXiv | 2020 | |
| 331 | Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data | âStability | ðNeurIPS'2021 | :octocat:Code | 2021 |
| 332 | Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method | âStability | ðarXiv'2020 | 2020 | |
| 333 | SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation | ð¡Defense | ðWWW | :octocat:Code | 2022 |
| 334 | Single Node Injection Attack against Graph Neural Networks | âAttack | ðCIKM | :octocat:Code | 2021 |
| 335 | Single-Node Attack for Fooling Graph Neural Networks | âAttack | ðKDD Workshop | :octocat:Code | 2021 |
| 336 | Smoothing Adversarial Training for GNN | ð¡Defense | ðIEEE TCSS | 2020 | |
| 337 | Sparse Vicious Attacks on Graph Neural Networks | âAttack | ðarXiv | :octocat:Code | 2022 |
| 338 | Spatially Focused Attack against Spatiotemporal Graph Neural Networks | âAttack | ðarXiv | 2021 | |
| 339 | Spatio-Temporal Sparsification for General Robust Graph Convolution Networks | ð¡Defense | ðarXiv | 2021 | |
| 340 | Spectral Adversarial Training for Robust Graph Neural Network | ð¡Defense | ðTKDE | :octocat:Code | 2022 |
| 341 | Speedup Robust Graph Structure Learning with Low-Rank Information | ð¡Defense | ðCIKM | 2021 | |
| 342 | Stability Properties of Graph Neural Networks | âStability | ðarXiv'2019 | 2019 | |
| 343 | Stability and Generalization Capabilities of Message Passing Graph Neural Networks | âStability | ðarXiv'2022 | 2022 | |
| 344 | Stability and Generalization of Graph Convolutional Neural Networks | âStability | ðKDD'2019 | 2019 | |
| 345 | Stability of Graph Convolutional Neural Networks to Stochastic Perturbations | âStability | ðarXiv'2021 | 2021 | |
| 346 | Stability of Graph Neural Networks to Relative Perturbations | âStability | ðICASSP'2020 | 2020 | |
| 347 | Stealing Links from Graph Neural Networks | âAttack | ðUSENIX Security | 2021 | |
| 348 | Structack: Structure-based Adversarial Attacks on Graph Neural Networks | âAttack | ðACM Hypertext | :octocat:Code | 2021 |
| 349 | Structural Attack against Graph Based Android Malware Detection | âAttack | ðCCS | 2021 | |
| 350 | Structure-Aware Hierarchical Graph Pooling using Information Bottleneck | ð¡Defense | ðIJCNN | 2021 | |
| 351 | Structured Adversarial Attack Towards General Implementation and Better Interpretability | âAttack | ðICLR | :octocat:Code | 2019 |
| 352 | Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks | âAttack | ðWSDM | 2022 | |
| 353 | TDGIA: Effective Injection Attacks on Graph Neural Networks | âAttack | ðKDD | :octocat:Code | 2021 |
| 354 | Target Defense Against Link-Prediction-Based Attacks via Evolutionary Perturbations | ð¡Defense | ðarXiv | 2019 | |
| 355 | Task and Model Agnostic Adversarial Attack on Graph Neural Networks | âAttack | ðarXiv | 2021 | |
| 356 | Tensor Graph Convolutional Networks for Multi-relational and Robust Learning | ð¡Defense | ðarXiv | 2020 | |
| 357 | The Robustness of Graph k-shell Structure under Adversarial Attacks | âAttack | ðarXiv | 2021 | |
| 358 | Time-aware Gradient Attack on Dynamic Network Link Prediction | âAttack | ðTKDE | 2021 | |
| 359 | Topological Effects on Attacks Against Vertex Classification | ð¡Defense | ðarXiv | 2020 | |
| 360 | Topological Relational Learning on Graphs | ð¡Defense | ðNeurIPS | :octocat:Code | 2021 |
| 361 | Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective | âAttack | ðIJCAI | :octocat:Code | 2019 |
| 362 | Towards More Practical Adversarial Attacks on Graph Neural Networks | âAttack | ðNeurIPS | :octocat:Code | 2020 |
| 363 | Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias | âAttack | ðNeurIPS | :octocat:Code | 2022 |
| 364 | Towards Revealing Parallel Adversarial Attack on Politician Socialnet of Graph Structure | âAttack | ðSecurity and Communication Networks | 2021 | |
| 365 | Towards Robust Graph Contrastive Learning | ð¡Defense | ðarXiv | 2021 | |
| 366 | Towards Robust Graph Neural Networks against Label Noise | ð¡Defense | ðICLR OpenReview | 2020 | |
| 367 | Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels | ð¡Defense | ðWSDM | :octocat:Code | 2022 |
| 368 | Towards Robust Graph Neural Networks via Adversarial Contrastive Learning | ð¡Defense | ðBigData | 2023 | |
| 369 | Towards Robust Reasoning over Knowledge Graphs | ð¡Defense | ðarXiv | 2021 | |
| 370 | Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Graphs | âAttack | ðarXiv | 2022 | |
| 371 | Towards a Unified Framework for Fair and Stable Graph Representation Learning | âStability | ðUAI'2021 | :octocat:Code | 2021 |
| 372 | Towards an Efficient and General Framework of Robust Training for Graph Neural Networks | ð¡Defense | ðICASSP | 2020 | |
| 373 | Towards an Optimal Asymmetric Graph Structure for Robust Semi-supervised Node Classification | ð¡Defense | ðKDD | 2022 | |
| 374 | Training Robust Graph Neural Network by Applying Lipschitz Constant Constraint | ðOthers | ðCentraleSupélec'2020 | :octocat:Code | 2020 |
| 375 | Training Stable Graph Neural Networks Through Constrained Learning | âStability | ðarXiv'2021 | 2021 | |
| 376 | Transferable Graph Backdoor Attack | âAttack | ðRAID | :octocat:Code | 2022 |
| 377 | Transferring Robustness for Graph Neural Network Against Poisoning Attacks | ð¡Defense | ðWSDM | :octocat:Code | 2020 |
| 378 | Trustworthy Graph Neural Networks: Aspects, Methods and Trends | ðSurvey | ðarXiv'2022 | 2022 | |
| 379 | UAG: Uncertainty-Aware Attention Graph Neural Network for Defending Adversarial Attacks | ð¡Defense | ðAAAI | 2021 | |
| 380 | UNTANGLE: Unlocking Routing and Logic Obfuscation Using Graph Neural Networks-based Link Prediction | âAttack | ðICCAD | :octocat:Code | 2021 |
| 381 | Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks | ð¡Defense | ðAAAI | 2021 | |
| 382 | Understanding Structural Vulnerability in Graph Convolutional Networks | ð¡Defense | ðIJCAI | :octocat:Code | 2021 |
| 383 | Understanding and Improving Graph Injection Attack by Promoting Unnoticeability | âAttack | ðICLR | :octocat:Code | 2022 |
| 384 | Unified Robust Training for Graph NeuralNetworks against Label Noise | ð¡Defense | ðarXiv | 2021 | |
| 385 | Universal Spectral Adversarial Attacks for Deformable Shapes | âAttack | ðCVPR | 2021 | |
| 386 | Unnoticeable Backdoor Attacks on Graph Neural Networks | âAttack | ðWWW | :octocat:Code | 2023 |
| 387 | Unsupervised Adversarially-Robust Representation Learning on Graphs | ð¡Defense | ðAAAI | :octocat:Code | 2022 |
| 388 | Unsupervised Euclidean Distance Attack on Network Embedding | âAttack | ðarXiv | 2019 | |
| 389 | Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation | âAttack | ðWWW | :octocat:Code | 2022 |
| 390 | Unveiling Anomalous Nodes Via Random Sampling and Consensus on Graphs | ð¡Defense | ðICASSP | 2021 | |
| 391 | Unveiling the potential of Graph Neural Networks for robust Intrusion Detection | ð¡Defense | ðarXiv | :octocat:Code | 2021 |
| 392 | VIKING: Adversarial Attack on Network Embeddings via Supervised Network Poisoning | âAttack | ðPAKDD | :octocat:Code | 2021 |
| 393 | Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings | ð¡Defense | ðNeurIPS | :octocat:Code | 2020 |
| 394 | Vertex Nomination, Consistent Estimation, and Adversarial Modification | âAttack | ðarXiv | 2019 | |
| 395 | Virtual Adversarial Training on Graph Convolutional Networks in Node Classification | ð¡Defense | ðPRCV | 2019 | |
| 396 | Watermarking Graph Neural Networks based on Backdoor Attacks | âAttack | ðarXiv | 2021 | |
| 397 | Watermarking Graph Neural Networks by Random Graphs | ðOthers | ðarXiv'2020 | 2020 | |
| 398 | We Cannot Guarantee Safety: The Undecidability of Graph Neural Network Verification | ðOthers | ðarXiv'2022 | 2022 | |
| 399 | What Does the Gradient Tell When Attacking the Graph Structure | âAttack | ðarXiv | 2022 | |
| 400 | When Do GNNs Work: Understanding and Improving Neighborhood Aggregation | âStability | ðIJCAI Workshop'2019 | :octocat:Code | 2019 |
| 401 | When Does Self-Supervision Help Graph Convolutional Networks? | ðOthers | ðICML'2020 | 2020 | |
| 402 | You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets | ð¡Defense | ðLoG | :octocat:Code | 2022 |
| 403 | αCyber: Enhancing Robustness of Android Malware Detection System against Adversarial Attacks on Heterogeneous Graph based Model | âAttack | ðCIKM | 2019 |