Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data

• URL: http://arxiv.org/abs/2607.07471v1
• Date: Wed, 08 Jul 2026 14:33:00 GMT
• Title: Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data
• Abstract summary: We present the first systematic evaluation of fairness interventions on private synthetic data.<n>We compare four pipeline configurations: (Baseline) training on original data; (DP-only) training on DP synthetic data; (Fair-only) applying fairness mechanisms on original data; and (DP+Fair) combining fairness mechanisms with DP synthetic data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness. Differential Privacy (DP) has become a gold standard for privacy-preserving data analysis, while fairness-aware mechanisms aim to mitigate discrimination against underrepresented groups. However, these objectives can conflict: DP often amplifies disparities across demographic groups, and little is known about whether established fairness interventions remain effective under DP constraints. In this work, we present, to our knowledge, the first systematic evaluation of fairness interventions on differentially private synthetic tabular data. Our benchmark centers on the Adaptive Iterative Mechanism (AIM), identified as the state-of-the-art marginal-based DP synthesizer (Cormode et al. 2025). We thus evaluate fairness interventions across four datasets, multiple group fairness metrics, and three categories of mitigation strategies (pre-processing, in-processing, and post-processing) under a wide range of privacy budgets. We compare four pipeline configurations: (Baseline) training on original data; (DP-only) training on DP synthetic data; (Fair-only) applying fairness mechanisms on original data; and (DP+Fair) combining fairness mechanisms with DP synthetic data. Our results demonstrate that while DP alone can degrade both utility and fairness, applying fairness interventions can partially restore equitable outcomes. Among them, post-processing methods tend to provide more stable fairness-utility trade-offs across privacy budgets and synthesizers, achieving strong fairness improvements while preserving competitive utility relative to other intervention stages. We release all code, data, and experimental artifacts in an open-source repository to ensure full reproducibility and to support future research on the privacy-fairness-utility trade-off.

Related papers

• Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms [9.177020525465272]
  We present the first comprehensive study of how fairness interventions affect membership inference privacy risks at the subpopulation level.<n>Our results demonstrate that fairness interventions do not uniformly increase privacy risk; their impact depends on model architecture, subgroup size, and mitigation strategy.
  arXiv  Detail & Related papers  (2026-07-16T06:10:42Z)
• Federated fairness-aware classification under differential privacy [9.340058165047717]
  We study the joint impact of differential privacy and fairness on classification in a federated setting.<n>We propose a two-step algorithm, namely FDP-Fair and CDP-Fair.<n>Our theoretical findings are complemented by extensive numerical experiments on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2026-03-25T15:09:12Z)
• Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification [6.28122931748758]
  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.
  arXiv  Detail & Related papers  (2025-11-24T08:31:02Z)
• Optimal Fairness under Local Differential Privacy [2.889268075288957]
  We investigate how to optimally design local differential privacy mechanisms that reduce data unfairness and thereby improve fairness in downstream classification.<n>As a theoretical contribution, we establish that for discrimination-accuracy optimal classifiers, reducing data unfairness necessarily leads to lower classification unfairness.<n> Empirically, we demonstrate that our approach consistently outperforms existing LDP mechanisms in reducing data unfairness across diverse datasets and fairness metrics.
  arXiv  Detail & Related papers  (2025-11-20T14:00:15Z)
• Targeted Learning for Data Fairness [52.59573714151884]
  We expand fairness inference by evaluating fairness in the data generating process itself.<n>We derive estimators demographic parity, equal opportunity, and conditional mutual information.<n>To validate our approach, we perform several simulations and apply our estimators to real data.
  arXiv  Detail & Related papers  (2025-02-06T18:51:28Z)
• SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI [3.548595326273084]
  SAFES is a Sequential PrivAcy and Fairness Enhancing data Synthesis procedure that sequentially combines DP data with a fairness-aware data preprocessing step.<n>We show that for reasonable privacy loss, SAFES-generated synthetic data can achieve significantly improved fairness metrics with relatively low utility loss.
  arXiv  Detail & Related papers  (2024-11-14T04:36:12Z)
• Incentives in Private Collaborative Machine Learning [56.84263918489519]
  Collaborative machine learning involves training models on data from multiple parties. We introduce differential privacy (DP) as an incentive. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2024-04-02T06:28:22Z)
• FairDP: Certified Fairness with Differential Privacy [55.51579601325759]
  This paper introduces FairDP, a novel training mechanism designed to provide group fairness certification for the trained model's decisions.<n>The key idea of FairDP is to train models for distinct individual groups independently, add noise to each group's gradient for data privacy protection, and integrate knowledge from group models to formulate a model that balances privacy, utility, and fairness in downstream tasks.
  arXiv  Detail & Related papers  (2023-05-25T21:07:20Z)
• Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy [51.11280118806893]
  We consider a federated data analytics problem in which a server coordinates the collaborative data analysis of multiple users with privacy concerns and limited communication capability. We study the local differential privacy guarantees of discrete-valued mechanisms with finite output space through the lens of $f$-differential privacy (DP) More specifically, we advance the existing literature by deriving tight $f$-DP guarantees for a variety of discrete-valued mechanisms.
  arXiv  Detail & Related papers  (2023-02-19T16:58:53Z)
• DP2-Pub: Differentially Private High-Dimensional Data Publication with Invariant Post Randomization [58.155151571362914]
  We propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases. splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable privacy budget. We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy.
  arXiv  Detail & Related papers  (2022-08-24T17:52:43Z)
• Post-processing of Differentially Private Data: A Fairness Perspective [53.29035917495491]
  This paper shows that post-processing causes disparate impacts on individuals or groups. It analyzes two critical settings: the release of differentially private datasets and the use of such private datasets for downstream decisions. It proposes a novel post-processing mechanism that is (approximately) optimal under different fairness metrics.
  arXiv  Detail & Related papers  (2022-01-24T02:45:03Z)
• Data Sharing Markets [95.13209326119153]
  We study a setup where each agent can be both buyer and seller of data. We consider two cases: bilateral data exchange (trading data with data) and unilateral data exchange (trading data with money)
  arXiv  Detail & Related papers  (2021-07-19T06:00:34Z)

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.