mlsanityData to 7 Oct 2026

Adversarial Attacks on Node Embeddings via Graph Poisoning

arXiv 1809.01093 ↗First posted 4 Sep 2018cs.LG cs.CR cs.SIcited by 109

Not on the map. Why?

Abstract (arXiv)

The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversarial vulnerability analysis on the widely used family of methods based on random walks. We derive efficient adversarial perturbations that poison the network structure and have a negative effect on both the quality of the embeddings and the downstream tasks. We further show that our attacks are transferable since they generalize to many models and are successful even when the attacker is restricted.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 22; 2023: 23; 2024: 22; 2025: 8; 2026: 6.

109 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  2. 2021Trustworthy AI: A Computational Perspectivecited by 93
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  4. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  5. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  6. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
  7. 2021LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysiscited by 65
  8. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  9. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  10. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  11. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  12. 2022Adversarial Graph Contrastive Learning with Information Regularizationcited by 38
38 more
  1. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  2. 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
  3. 2022Amplifying Membership Exposure via Data Poisoningcited by 29
  4. 2022Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagationcited by 25
  5. 2024Spectral Graph Pruning Against Over-Squashing and Over-Smoothingcited by 23
  6. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  7. 2021Adversarial Attack on Graph Neural Networks as An Influence Maximization Problemcited by 20
  8. 2021Graph Structural Attack by Perturbing Spectral Distancecited by 16
  9. 2022DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networkscited by 16
  10. 2022Characterizing the Influence of Graph Elementscited by 16
  11. 2022Projective Ranking-based GNN Evasion Attackscited by 14
  12. 2022Strategic Classification with Graph Neural Networkscited by 14
  13. 2021Get a Model! Model Hijacking Attack Against Machine Learning Modelscited by 13
  14. 2021CogDL: A Comprehensive Library for Graph Deep Learningcited by 12
  15. 2021Poisoning Knowledge Graph Embeddings via Relation Inference Patternscited by 12
  16. 2022LPGNet: Link Private Graph Networks for Node Classificationcited by 12
  17. 2022Adversarial Camouflage for Node Injection Attack on Graphscited by 11
  18. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  19. 2021Adversarial Attack Framework on Graph Embedding Models with Limited Knowledgecited by 10
  20. 2021Robust Graph Neural Networks via Probabilistic Lipschitz Constraintscited by 10
  21. 2023SlothSpeech: Denial-of-service Attack Against Speech Recognition Modelscited by 9
  22. 2023Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphscited by 9
  23. 2022Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classificationcited by 8
  24. 2021Query Driven-Graph Neural Networks for Community Search: From Non-Attributed, Attributed, to Interactive Attributedcited by 6
  25. 2023Similarity Preserving Adversarial Graph Contrastive Learningcited by 6
  26. 2023Deceptive Fairness Attacks on Graphs via Meta Learningcited by 6
  27. 2021Adversarial Attack on Network Embeddings via Supervised Network Poisoningcited by 5
  28. 2021Adversarial Attacks on Graph Classification via Bayesian Optimisationcited by 5
  29. 2021Task and Model Agnostic Adversarial Attack on Graph Neural Networkscited by 5
  30. 2022ARIEL: Adversarial Graph Contrastive Learningcited by 5
  31. 2023Node Injection for Class-specific Network Poisoningcited by 5
  32. 2023On the Security Risks of Knowledge Graph Reasoningcited by 5
  33. 2024Backdoor Graph Condensationcited by 5
  34. 2021Adversarially Regularized Graph Attention Networks for Inductive Learning on Partially Labeled Graphscited by 4
  35. 2021Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attackscited by 4
  36. 2022Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspectivecited by 4
  37. 2022Learning Robust Representation through Graph Adversarial Contrastive Learningcited by 4
  38. 2023GNN-Ensemble: Towards Random Decision Graph Neural Networkscited by 4

50 most cited of 109 All 109 (JSON)