{"total":71,"rows":[{"id":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118,"area":null},{"id":"2110.14038","title":"Robustness of Graph Neural Networks at Scale","created":"2021-10-26","cited_by_count":100,"area":null},{"id":"2112.08331","title":"Model Stealing Attacks Against Inductive Graph Neural Networks","created":"2021-12-15","cited_by_count":50,"area":null},{"id":"2108.02183","title":"Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization","created":"2021-08-04","cited_by_count":27,"area":null},{"id":"2209.07807","title":"Model Inversion Attacks against Graph Neural Networks","created":"2022-09-16","cited_by_count":26,"area":null},{"id":"2106.07767","title":"How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications","created":"2021-06-14","cited_by_count":21,"area":null},{"id":"2202.10107","title":"Model-Agnostic Augmentation for Accurate Graph Classification","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2106.10785","title":"Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem","created":"2021-06-21","cited_by_count":20,"area":null},{"id":"2203.03153","title":"Scalable Verification of GNN-based Job Schedulers","created":"2022-03-07","cited_by_count":19,"area":null},{"id":"2406.03193","title":"Graph Neural Network Explanations are Fragile","created":"2024-06-05","cited_by_count":19,"area":null},{"id":"2108.03388","title":"Jointly Attacking Graph Neural Network and its Explanations","created":"2021-08-07","cited_by_count":18,"area":null},{"id":"2202.03898","title":"Verification-Aided Deep Ensemble Selection","created":"2022-02-08","cited_by_count":18,"area":null},{"id":"2111.00684","title":"Graph Structural Attack by Perturbing Spectral Distance","created":"2021-11-01","cited_by_count":16,"area":null},{"id":"2304.00010","title":"Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias","created":"2023-03-29","cited_by_count":16,"area":null},{"id":"2209.05957","title":"Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks","created":"2022-09-13","cited_by_count":12,"area":null},{"id":"2302.05745","title":"Verifying Generalization in Deep Learning","created":"2023-02-11","cited_by_count":11,"area":null},{"id":"2405.11034","title":"Safety in Graph Machine Learning: Threats and Safeguards","created":"2024-05-17","cited_by_count":11,"area":null},{"id":"2407.12068","title":"Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness","created":"2024-07-16","cited_by_count":11,"area":null},{"id":"2105.12419","title":"Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge","created":"2021-05-26","cited_by_count":10,"area":null},{"id":"2301.02039","title":"Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks","created":"2023-01-05","cited_by_count":10,"area":null},{"id":"2402.13937","title":"Verifying message-passing neural networks via topology-based bounds tightening","created":"2024-02-21","cited_by_count":10,"area":null},{"id":"2205.03546","title":"Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guarantees","created":"2022-05-07","cited_by_count":9,"area":null},{"id":"2206.05070","title":"Fundamental Limits in Formal Verification of Message-Passing Neural Networks","created":"2022-06-10","cited_by_count":9,"area":null},{"id":"2308.10779","title":"Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs","created":"2023-08-21","cited_by_count":9,"area":null},{"id":"2310.16221","title":"Hierarchical Randomized Smoothing","created":"2023-10-24","cited_by_count":9,"area":null},{"id":"2401.04331","title":"Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Study","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2101.06855","title":"GraphAttacker: A General Multi-Task GraphAttack Framework","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2208.06651","title":"Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification","created":"2022-08-13","cited_by_count":8,"area":null},{"id":"2410.13761","title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2302.13875","title":"Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2104.09369","title":"Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models","created":"2021-04-19","cited_by_count":5,"area":null},{"id":"2107.10302","title":"Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks","created":"2021-07-11","cited_by_count":5,"area":null},{"id":"2111.02842","title":"Adversarial Attacks on Graph Classification via Bayesian Optimisation","created":"2021-11-04","cited_by_count":5,"area":null},{"id":"2112.13267","title":"Task and Model Agnostic Adversarial Attack on Graph Neural Networks","created":"2021-12-25","cited_by_count":5,"area":null},{"id":"2110.10482","title":"Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2310.13822","title":"Adversarial Attacks on Fairness of Graph Neural Networks","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2104.15061","title":"Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense","created":"2021-04-30","cited_by_count":3,"area":null},{"id":"2405.05784","title":"Link Stealing Attacks Against Inductive Graph Neural Networks","created":"2024-05-09","cited_by_count":3,"area":null},{"id":"2412.13134","title":"Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2504.13786","title":"On the Relationship Between Robustness and Expressivity of Graph Neural Networks","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2508.04894","title":"Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)","created":"2025-08-06","cited_by_count":3,"area":null},{"id":"2201.05819","title":"Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2208.12815","title":"What Does the Gradient Tell When Attacking the Graph Structure","created":"2022-08-26","cited_by_count":2,"area":null},{"id":"2308.15614","title":"Everything Perturbed All at Once: Enabling Differentiable Graph Attacks","created":"2023-08-29","cited_by_count":2,"area":null},{"id":"2407.19155","title":"Debiased Graph Poisoning Attack via Contrastive Surrogate Objective","created":"2024-07-27","cited_by_count":2,"area":null},{"id":"2503.18503","title":"Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2510.10849","title":"Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2602.06240","title":"ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2205.14440","title":"Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks","created":"2022-05-28","cited_by_count":1,"area":null},{"id":"2211.08068","title":"Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2311.13244","title":"Hard Label Black Box Node Injection Attack on Graph Neural Networks","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2311.16139","title":"GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models","created":"2023-11-03","cited_by_count":1,"area":null},{"id":"2407.18170","title":"RIDA: A Robust Attack Framework on Incomplete Graphs","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2408.10948","title":"GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2501.05015","title":"On Measuring Unnoticeability of Graph Adversarial Attacks: Observations, New Measure, and Applications","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2110.02631","title":"Inference Attacks Against Graph Neural Networks","created":"2021-10-06","cited_by_count":0,"area":null},{"id":"2306.07758","title":"Generated Graph Detection","created":"2023-06-13","cited_by_count":0,"area":null},{"id":"2308.11754","title":"Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detection","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2311.01205","title":"Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2312.10943","title":"Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2401.03790","title":"Inferring Properties of Graph Neural Networks","created":"2024-01-08","cited_by_count":0,"area":null},{"id":"2403.09901","title":"Robust Subgraph Learning by Monitoring Early Training Representations","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2405.08645","title":"Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretation","created":"2024-05-14","cited_by_count":0,"area":null},{"id":"2411.02809","title":"Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2505.08320","title":"Adaptive Branch Specialization in Spectral-Spatial Graph Neural Networks for Certified Robustness","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2509.25418","title":"Leveraging Vulnerabilities in Temporal Graph Neural Networks via Strategic High-Impact Assaults","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.12233","title":"Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2511.07170","title":"On Stealing Graph Neural Network Models","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2603.20746","title":"Adversarial Attacks on Locally Private Graph Neural Networks","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2603.21155","title":"Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphs","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2607.07089","title":"Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}