mlsanityData to 7 Oct 2026

Adversarial Attacks on Fairness of Graph Neural Networks

arXiv 2310.13822 ↗First posted 20 Oct 2023cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based applications. Although these methods greatly improve the algorithmic fairness of GNNs, the fairness can be easily corrupted by carefully designed adversarial attacks. In this paper, we investigate the problem of adversarial attacks on fairness of GNNs and propose G-FairAttack, a general framework for attacking various types of fairness-aware GNNs in terms of fairness with an unnoticeable effect on prediction utility. In addition, we propose a fast computation technique to reduce the time complexity of G-FairAttack. The experimental study demonstrates that G-FairAttack successfully corrupts the fairness of different types of GNNs while keeping the attack unnoticeable. Our study on fairness attacks sheds light on potential vulnerabilities in fairness-aware GNNs and guides further research on the robustness of GNNs in terms of fairness.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 55 of its 70 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

55 of 70 references.

References · 55

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  11. 2018Adversarial Attack on Graph Structured Datacited by 300
  12. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
38 more
  1. 2018Adversarial Attacks and Defences: A Surveycited by 259
  2. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  3. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  4. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  5. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  6. 2016GRAM: Graph-based Attention Model for Healthcare Representation Learningcited by 152
  7. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  8. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  9. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  10. 2018Stronger Data Poisoning Attacks Break Data Sanitization Defensescited by 125
  11. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  12. 2020GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Mediacited by 108
  13. 2021Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendationcited by 101
  14. 2021Robustness of Graph Neural Networks at Scalecited by 100
  15. 2020MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimationcited by 99
  16. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  17. 2021Graph Representation Learning in Biomedicinecited by 79
  18. 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
  19. 2022Fairness in Graph Mining: A Surveycited by 76
  20. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  21. 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
  22. 2022Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakagecited by 61
  23. 2020Poisoning Attacks on Algorithmic Fairnesscited by 58
  24. 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
  25. 2020Exacerbating Algorithmic Bias through Fairness Attackscited by 47
  26. 2022TwiBot-22: Towards Graph-Based Twitter Bot Detectioncited by 44
  27. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  28. 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
  29. 2021Fair Representation Learning for Heterogeneous Information Networkscited by 28
  30. 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
  31. 2021Adversarial Attack on Graph Neural Networks as An Influence Maximization Problemcited by 20
  32. 2021Poisoning Attacks on Fair Machine Learningcited by 19
  33. 2022Interpreting Unfairness in Graph Neural Networks via Training Node Attributioncited by 18
  34. 2021Graph Structural Attack by Perturbing Spectral Distancecited by 16
  35. 2019Node Injection Attacks on Graphs via Reinforcement Learningcited by 15
  36. 2021InfoFair: Information-Theoretic Intersectional Fairnesscited by 15
  37. 2022On Structural Explanation of Bias in Graph Neural Networkscited by 15
  38. 2022Projective Ranking-based GNN Evasion Attackscited by 14

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3.

4 papers.

  1. 2024Safety in Graph Machine Learning: Threats and Safeguardscited by 11
  2. 2024Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injectionscited by 2
  3. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2
  4. 2023Fair Graph Machine Learning under Adversarial Missingness Processescited by 0