mlsanityData to 7 Oct 2026

Poisoning Attacks on Algorithmic Fairness

arXiv 2004.07401 ↗First posted 15 Apr 2020cs.LG cs.CR cs.CYcited by 58

Not on the map. Why?

Abstract (arXiv)

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model accuracy of such poisoning attacks have been widely studied, their potential effects on other model performance metrics remain to be evaluated. In this work, we introduce an optimization framework for poisoning attacks against algorithmic fairness, and develop a gradient-based poisoning attack aimed at introducing classification disparities among different groups in the data. We empirically show that our attack is effective not only in the white-box setting, in which the attacker has full access to the target model, but also in a more challenging black-box scenario in which the attacks are optimized against a substitute model and then transferred to the target model. We believe that our findings pave the way towards the definition of an entirely novel set of adversarial attacks targeting algorithmic fairness in different scenarios, and that investigating such vulnerabilities will help design more robust algorithms and countermeasures in the future.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 16; 2024: 10; 2025: 7; 2026: 2.

58 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  2. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  4. 2022Fairness in Graph Mining: A Surveycited by 76
  5. 2021Sample Selection for Fair and Robust Trainingcited by 48
  6. 2022Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Modelscited by 47
  7. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  8. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  9. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  10. 2022Robust Conversational Agents against Imperceptible Toxicity Triggerscited by 23
  11. 2025Data Poisoning in Deep Learning: A Surveycited by 20
  12. 2021Poisoning Attacks on Fair Machine Learningcited by 19
38 more
  1. 2021Fairness-Aware PAC Learning from Corrupted Datacited by 18
  2. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  3. 2021Fooling Partial Dependence via Data Poisoningcited by 16
  4. 2021Algorithmic Fairness Verification with Graphical Modelscited by 16
  5. 2023Improving Fair Training under Correlation Shiftscited by 14
  6. 2022Robust Fair Clustering: A Novel Fairness Attack and Defense Frameworkcited by 13
  7. 2022Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networkscited by 12
  8. 2023Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoningcited by 10
  9. 2024Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Modelscited by 10
  10. 2022Towards Multi-Objective Statistically Fair Federated Learningcited by 8
  11. 2022How Biased are Your Features?: Computing Fairness Influence Functions with Global Sensitivity Analysiscited by 7
  12. 2023Deceptive Fairness Attacks on Graphs via Meta Learningcited by 6
  13. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  14. 2024Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspectivecited by 6
  15. 2021Machine Learning for Fraud Detection in E-Commerce: A Research Agendacited by 5
  16. 2021Fairness Degrading Adversarial Attacks Against Clustering Algorithmscited by 5
  17. 2022Subverting Fair Image Search with Generative Adversarial Perturbationscited by 5
  18. 2022FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Datacited by 5
  19. 2023Fairness Hacking: The Malicious Practice of Shrouding Unfairness in Algorithmscited by 5
  20. 2022Breaking Fair Binary Classification with Optimal Flipping Attackscited by 4
  21. 2022Fairness-aware Regression Robust to Adversarial Attackscited by 4
  22. 2023Adversarial Attacks on Fairness of Graph Neural Networkscited by 4
  23. 2024EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learningcited by 4
  24. 2024BadFair: Backdoored Fairness Attacks with Group-conditioned Triggerscited by 4
  25. 2023Towards Poisoning Fair Representationscited by 3
  26. 2024The Effect of Data Poisoning on Counterfactual Explanationscited by 3
  27. 2024FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?cited by 3
  28. 2023To be Robust and to be Fair: Aligning Fairness with Robustnesscited by 2
  29. 2023TrojFair: Trojan Fairness Attackscited by 2
  30. 2024Multigroup Robustnesscited by 2
  31. 2024Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injectionscited by 2
  32. 2023Understanding Variation in Subpopulation Susceptibility to Poisoning Attackscited by 1
  33. 2023Attacks on fairness in Federated Learningcited by 1
  34. 2023Attacking Byzantine Robust Aggregation in High Dimensionscited by 1
  35. 2025Covert Attacks on Machine Learning Training in Passively Secure MPCcited by 1
  36. 2025In-Context Bias Propagation in LLM-Based Tabular Data Generationcited by 1
  37. 2023Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomycited by 0
  38. 2023Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognitioncited by 0

50 most cited of 58 All 58 (JSON)