mlsanityData to 14 Oct 2026

Attacking Graph Convolutional Networks via Rewiring

arXiv 1906.03750 ↗First posted 10 Jun 2019cs.LG cs.CR stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which deliberately add carefully created unnoticeable perturbation to the graph structure. The perturbation is usually created by adding/deleting a few edges, which might be noticeable even when the number of edges modified is small. In this paper, we propose a graph rewiring operation which affects the graph in a less noticeable way compared to adding/deleting edges. We then use reinforcement learning to learn the attack strategy based on the proposed rewiring operation. Experiments on real world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation to the graph structure affects the output of the target model.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 8; 2023: 5; 2024: 6; 2025: 1.

32 papers.

Sort:

  1. 2021Trustworthy AI: A Computational Perspectivecited by 93
  2. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  3. 2021A Hard Label Black-box Adversarial Attack Against Graph Neural Networkscited by 26
  4. 2022Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationcited by 25
  5. 2022Reinforcement learning on graphs: A surveycited by 20
  6. 2022Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learningcited by 19
  7. 2021Jointly Attacking Graph Neural Network and its Explanationscited by 18
  8. 2021Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learningcited by 17
  9. 2023Robust Mid-Pass Filtering Graph Convolutional Networkscited by 17
  10. 2023Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debiascited by 16
  11. 2022Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networkscited by 12
  12. 2023BeMap: Balanced Message Passing for Fair Graph Neural Networkcited by 11
20 more
  1. 2024Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustnesscited by 11
  2. 2022Are Gradients on Graph Structure Reliable in Gray-box Attacks?cited by 10
  3. 2021Structack: Structure-based Adversarial Attacks on Graph Neural Networkscited by 8
  4. 2024Minimum Topology Attacks for Graph Neural Networkscited by 6
  5. 2021Adversarial Attacks on Graph Classification via Bayesian Optimisationcited by 5
  6. 2021Task and Model Agnostic Adversarial Attack on Graph Neural Networkscited by 5
  7. 2021Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attackscited by 4
  8. 2021Reinforcement Learning For Data Poisoning on Graph Neural Networkscited by 3
  9. 2021Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defensecited by 3
  10. 2022Dynamic Network Reconfiguration for Entropy Maximization using Deep Reinforcement Learningcited by 3
  11. 2024Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Methodcited by 3
  12. 2022What Does the Gradient Tell When Attacking the Graph Structurecited by 2
  13. 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbationscited by 2
  14. 2021Adversarial Robustness of Probabilistic Network Embedding for Link Predictioncited by 1
  15. 2023Explainability-Based Adversarial Attack on Graphs Through Edge Perturbationcited by 1
  16. 2024GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximizationcited by 1
  17. 2022Black-box Node Injection Attack for Graph Neural Networkscited by 0
  18. 2023Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detectioncited by 0
  19. 2024Adversary-Robust Graph-Based Learning of WSIscited by 0
  20. 2024Certifying Robustness of Graph Convolutional Networks for Node Perturbation with Polyhedra Abstract Interpretationcited by 0