# Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks

arXiv: https://arxiv.org/abs/2209.05957 · HTML: https://mlsanity.com/paper/2209.05957/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 13 Sep 2022.

## Builds on (most cited first, 30 of 33)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Adversarial Attacks on Graph Neural Networks via Meta Learning](https://mlsanity.com/paper/1902.08412/) (2019)
- [Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective](https://mlsanity.com/paper/1906.04214/) (2019)
- [GNNGuard: Defending Graph Neural Networks against Adversarial Attacks](https://mlsanity.com/paper/2006.08149/) (2020)
- [Is Homophily a Necessity for Graph Neural Networks?](https://mlsanity.com/paper/2106.06134/) (2021)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [Compositional Fairness Constraints for Graph Embeddings](https://mlsanity.com/paper/1905.10674/) (2019)
- [Robustness of Graph Neural Networks at Scale](https://mlsanity.com/paper/2110.14038/) (2021)
- [DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses](https://mlsanity.com/paper/2005.06149/) (2020)
- [Hiding Individuals and Communities in a Social Network](https://mlsanity.com/paper/1608.00375/) (2016)
- [Towards More Practical Adversarial Attacks on Graph Neural Networks](https://mlsanity.com/paper/2006.05057/) (2020)
- [Subgroup Generalization and Fairness of Graph Neural Networks](https://mlsanity.com/paper/2106.15535/) (2021)
- [FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning](https://mlsanity.com/paper/2104.14210/) (2021)
- [Poisoning Attacks on Algorithmic Fairness](https://mlsanity.com/paper/2004.07401/) (2020)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [Attacking Graph-based Classification via Manipulating the Graph Structure](https://mlsanity.com/paper/1903.00553/) (2019)
- [Exacerbating Algorithmic Bias through Fairness Attacks](https://mlsanity.com/paper/2012.08723/) (2020)
- [Attacking Graph Convolutional Networks via Rewiring](https://mlsanity.com/paper/1906.03750/) (2019)
- [MGA: Momentum Gradient Attack on Network](https://mlsanity.com/paper/2002.11320/) (2020)

## Built on by (most cited first, 12 of 12)

- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach](https://mlsanity.com/paper/2310.06396/) (2023)
- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND](https://mlsanity.com/paper/2404.17099/) (2024)
- [A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions](https://mlsanity.com/paper/2308.13821/) (2023)
- [Safety in Graph Machine Learning: Threats and Safeguards](https://mlsanity.com/paper/2405.11034/) (2024)
- [Deceptive Fairness Attacks on Graphs via Meta Learning](https://mlsanity.com/paper/2310.15653/) (2023)
- [Adversarial Attacks on Fairness of Graph Neural Networks](https://mlsanity.com/paper/2310.13822/) (2023)
- [Equipping Federated Graph Neural Networks with Structure-aware Group Fairness](https://mlsanity.com/paper/2310.12350/) (2023)
- [Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections](https://mlsanity.com/paper/2406.03052/) (2024)
- [Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks](https://mlsanity.com/paper/2310.15656/) (2023)
- [Fair Graph Machine Learning under Adversarial Missingness Processes](https://mlsanity.com/paper/2311.01591/) (2023)

## Abstract (arXiv)

We present evidence for the existence and effectiveness of adversarial attacks on graph neural networks (GNNs) that aim to degrade fairness. These attacks can disadvantage a particular subgroup of nodes in GNN-based node classification, where nodes of the underlying network have sensitive attributes, such as race or gender. We conduct qualitative and experimental analyses explaining how adversarial link injection impairs the fairness of GNN predictions. For example, an attacker can compromise the fairness of GNN-based node classification by injecting adversarial links between nodes belonging to opposite subgroups and opposite class labels. Our experiments on empirical datasets demonstrate that adversarial fairness attacks can significantly degrade the fairness of GNN predictions (attacks are effective) with a low perturbation rate (attacks are efficient) and without a significant drop in accuracy (attacks are deceptive). This work demonstrates the vulnerability of GNN models to adversarial fairness attacks. We hope our findings raise awareness about this issue in our community and lay a foundation for the future development of GNN models that are more robust to such attacks.