Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification

• URL: http://arxiv.org/abs/2511.18876v1
• Date: Mon, 24 Nov 2025 08:31:02 GMT
• Title: Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
• Authors: Lilian Say, Christophe Denis, Rafael Pinot,
• Abstract summary: We show that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees.<n>We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy.<n>Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate as the best non-private methods from the literature.
• Score: 6.28122931748758
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-populations. While privacy and fairness have each been extensively studied, their joint treatment remains poorly understood. Existing research often frames them as conflicting objectives, with multiple studies suggesting that strong privacy notions such as differential privacy inevitably compromise fairness. In this work, we challenge that perspective by showing that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees. We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy. Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate (up logarithmic factor) as the best non-private methods from the literature. Experiments on both synthetic and real datasets confirm our theoretical results, showing that the proposed algorithm achieves state-of-the-art accuracy/fairness/privacy trade-offs.

Related papers

• Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility [28.676852732262407]
  Federated Learning (FL) enables collaborative model training without data sharing.<n>We introduce a differentially private fair FL algorithm that transforms this multi-objective optimization into a zero-sum game.<n>Our theoretical analysis reveals a surprising inverse relationship, i.e., stricter privacy protection limits the system's ability to detect and correct demographic biases.
  arXiv  Detail & Related papers  (2025-10-30T07:14:55Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• Enforcing Demographic Coherence: A Harms Aware Framework for Reasoning about Private Data Release [14.939460540040459]
  We introduce demographic coherence, a condition inspired by privacy attacks that we argue is necessary for data privacy.<n>Our framework focuses on confidence rated predictors, which can in turn be distilled from almost any data-informed process.<n>We prove that every differentially private data release is also demographically coherent, and that there are demographically coherent algorithms which are not differentially private.
  arXiv  Detail & Related papers  (2025-02-04T20:42:30Z)
• Differentially Private Random Feature Model [47.35176457481132]
  We produce a differentially private random feature model for privacy-preserving kernel machines.<n>We show that our method preserves privacy and derive a generalization error bound for the method.
  arXiv  Detail & Related papers  (2024-12-06T05:31:08Z)
• A Stochastic Optimization Framework for Private and Fair Learning From Decentralized Data [14.748203847227542]
  We develop a novel algorithm for private and fair federated learning (FL) Our algorithm satisfies inter-silo record-level differential privacy (ISRL-DP) Experiments demonstrate the state-of-the-art fairness-accuracy framework tradeoffs of our algorithm across different privacy levels.
  arXiv  Detail & Related papers  (2024-11-12T15:51:35Z)
• Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacy [64.32494202656801]
  Privacy-preserving computer vision is an important emerging problem in machine learning and artificial intelligence.<n>We present anonymization pipeline that replaces sensitive human subjects in video datasets with synthetic avatars within context.<n>We also proposeMaskDP to protect non-anonymized but privacy sensitive background information.
  arXiv  Detail & Related papers  (2024-10-22T15:22:53Z)
• Private Estimation when Data and Privacy Demands are Correlated [5.755004576310333]
  Differential Privacy is the current gold-standard for ensuring privacy for statistical queries.<n>We consider the problems of empirical mean estimation for univariate data and frequency estimation for categorical data.<n>We establish theoretical performance guarantees for our proposed algorithms, under both PAC error and mean-squared error.
  arXiv  Detail & Related papers  (2024-07-15T22:46:02Z)
• Privacy at a Price: Exploring its Dual Impact on AI Fairness [24.650648702853903]
  We show that differential privacy in machine learning models can unequally impact separate demographic subgroups regarding prediction accuracy. This leads to a fairness concern, and manifests as biased performance. implementing gradient clipping in the differentially private gradient descent ML method can mitigate the negative impact of DP noise on fairness.
  arXiv  Detail & Related papers  (2024-04-15T00:23:41Z)
• TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data [50.797729676285876]
  We propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-16T16:41:14Z)
• Theoretically Principled Federated Learning for Balancing Privacy and Utility [61.03993520243198]
  We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters. It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning.
  arXiv  Detail & Related papers  (2023-05-24T13:44:02Z)
• Smooth Anonymity for Sparse Graphs [69.1048938123063]
  differential privacy has emerged as the gold standard of privacy, however, when it comes to sharing sparse datasets. In this work, we consider a variation of $k$-anonymity, which we call smooth-$k$-anonymity, and design simple large-scale algorithms that efficiently provide smooth-$k$-anonymity.
  arXiv  Detail & Related papers  (2022-07-13T17:09:25Z)
• Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach [54.32266555843765]
  This paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors. The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints.
  arXiv  Detail & Related papers  (2020-09-26T10:50:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.