mlsanityData to 7 Oct 2026

Scalable Attack on Graph Data by Injecting Vicious Nodes

arXiv 2004.13825 ↗First posted 22 Apr 2020cs.CR cs.LGcited by 50

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that graph convolution networks (GCNs) are vulnerable to carefully designed attacks, which aim to cause misclassification of a specific node on the graph with unnoticeable perturbations. However, a vast majority of existing works cannot handle large-scale graphs because of their high time complexity. Additionally, existing works mainly focus on manipulating existing nodes on the graph, while in practice, attackers usually do not have the privilege to modify information of existing nodes. In this paper, we develop a more scalable framework named Approximate Fast Gradient Sign Method (AFGSM) which considers a more practical attack scenario where adversaries can only inject new vicious nodes to the graph while having no control over the original graph. Methodologically, we provide an approximation strategy to linearize the model we attack and then derive an approximate closed-from solution with a lower time cost. To have a fair comparison with existing attack methods that manipulate the original graph, we adapt them to the new attack scenario by injecting vicious nodes. Empirical experimental results show that our proposed attack method can significantly reduce the classification accuracy of GCNs and is much faster than existing methods without jeopardizing the attack performance.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 16; 2023: 7; 2024: 11; 2025: 10; 2026: 2.

50 papers.

Sort:

  1. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  2. 2021Robustness of Graph Neural Networks at Scalecited by 100
  3. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  4. 2021TDGIA:Effective Injection Attacks on Graph Neural Networkscited by 67
  5. 2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
  6. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  7. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  8. 2022On the Robustness of Graph Neural Diffusion to Topology Perturbationscited by 30
  9. 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approachcited by 24
  10. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  11. 2022Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learningcited by 19
  12. 2024Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FRONDcited by 16
38 more
  1. 2022Adversarial Camouflage for Node Injection Attack on Graphscited by 11
  2. 2022Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attackcited by 10
  3. 2022GANI: Global Attacks on Graph Neural Networks via Imperceptible Node Injectionscited by 10
  4. 2024Verifying message-passing neural networks via topology-based bounds tighteningcited by 10
  5. 2022Fundamental Limits in Formal Verification of Message-Passing Neural Networkscited by 9
  6. 2024Coupling Graph Neural Networks with Fractional Order Continuous Dynamics: A Robustness Studycited by 9
  7. 2024Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Levelcited by 9
  8. 2022Neighboring Backdoor Attacks on Graph Convolutional Networkcited by 7
  9. 2022Sparse Vicious Attacks on Graph Neural Networkscited by 5
  10. 2023Node Injection for Class-specific Network Poisoningcited by 5
  11. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  12. 2025TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attackscited by 5
  13. 2023IDEA: Invariant Defense for Graph Adversarial Robustnesscited by 4
  14. 2024Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedgescited by 4
  15. 2022Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantationcited by 3
  16. 2023Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learningcited by 3
  17. 2025Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspectivecited by 3
  18. 2023Graph Adversarial Immunization for Certifiable Robustnesscited by 2
  19. 2024Fast Inference of Removal-Based Node Influencecited by 2
  20. 2024Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injectionscited by 2
  21. 2022Towards Explanation for Unsupervised Graph-Level Representation Learningcited by 1
  22. 2022Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentationcited by 1
  23. 2023Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networkscited by 1
  24. 2024Effective backdoor attack on graph neural networks in link prediction taskscited by 1
  25. 2024AGSOA:Graph Neural Network Targeted Attack Based on Average Gradient and Structure Optimizationcited by 1
  26. 2024Adversarial Robustness of Graph Transformerscited by 1
  27. 2025LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injectioncited by 1
  28. 2025Adverseness vs. Equilibrium: Exploring Graph Adversarial Resilience through Dynamic Equilibriumcited by 1
  29. 2025HeTa: Relation-wise Heterogeneous Graph Foundation Attack Modelcited by 1
  30. 2022Black-box Node Injection Attack for Graph Neural Networkscited by 0
  31. 2024Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectorscited by 0
  32. 2025How Feasible is Augmenting Fake Nodes with Learnable Features as a Counter-strategy against Link Stealing Attacks?cited by 0
  33. 2025Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attackscited by 0
  34. 2025JANUS: A Dual-Constraint Generative Framework for Stealthy Node Injection Attackscited by 0
  35. 2025Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGscited by 0
  36. 2025GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNscited by 0
  37. 2026Single-Edge Node Injection Threats to GNN-Based Security Monitoring in Industrial Graph Systemscited by 0
  38. 2026PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passingcited by 0