SCIENCE@home

Adversarial Bias: Data Poisoning Attacks on Fairness

Eunice Chan,Hanghang Tong

Published 2025 in BigData Congress [Services Society]

ABSTRACT

With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. In this work, we first provide a theoretical analysis demonstrating that a simple adversarial poisoning strategy is sufficient to induce maximally unfair behavior in naive Bayes classifiers. Our key idea is to strategically inject a small fraction of carefully-crafted adversarial data points into the training set, biasing the model's decision boundary to disproportionately affect a protected group while preserving generalizable performance. To illustrate the practical effectiveness of our method, we conduct experiments across three benchmark datasets and models. We find that our attack significantly outperforms existing methods in degrading fairness metrics across multiple models and datasets, often achieving substantially higher levels of unfairness with a comparable or only slightly worse impact on accuracy. Notably, our method proves effective on a wide range of models, in contrast to prior work, demonstrating a robust and potent approach to compromising the fairness of machine learning systems.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-19 of 19 references · Page 1 of 1

CITED BY

  • No citing papers are available for this paper.

Showing 0-0 of 0 citing papers · Page 1 of 1