Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation

• URL: http://arxiv.org/abs/2508.21815v1
• Date: Fri, 29 Aug 2025 17:51:42 GMT
• Title: Achieving Hilbert-Schmidt Independence Under Rényi Differential Privacy for Fair and Private Data Generation
• Abstract summary: Synthetic data generation has emerged as a promising solution to risk-aware data sharing and model development.<n>We propose (Fair Latent Intervention under Privacy guarantees) to address both privacy and fairness concerns in this setting.<n>Unlike the typical setup in fairness-aware data generation, we assume a task-agnostic setup, not reliant on a fixed, defined downstream task, thus offering broader applicability.
• Score: 5.428917824315977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As privacy regulations such as the GDPR and HIPAA and responsibility frameworks for artificial intelligence such as the AI Act gain traction, the ethical and responsible use of real-world data faces increasing constraints. Synthetic data generation has emerged as a promising solution to risk-aware data sharing and model development, particularly for tabular datasets that are foundational to sensitive domains such as healthcare. To address both privacy and fairness concerns in this setting, we propose FLIP (Fair Latent Intervention under Privacy guarantees), a transformer-based variational autoencoder augmented with latent diffusion to generate heterogeneous tabular data. Unlike the typical setup in fairness-aware data generation, we assume a task-agnostic setup, not reliant on a fixed, defined downstream task, thus offering broader applicability. To ensure privacy, FLIP employs R\'enyi differential privacy (RDP) constraints during training and addresses fairness in the input space with RDP-compatible balanced sampling that accounts for group-specific noise levels across multiple sampling rates. In the latent space, we promote fairness by aligning neuron activation patterns across protected groups using Centered Kernel Alignment (CKA), a similarity measure extending the Hilbert-Schmidt Independence Criterion (HSIC). This alignment encourages statistical independence between latent representations and the protected feature. Empirical results demonstrate that FLIP effectively provides significant fairness improvements for task-agnostic fairness and across diverse downstream tasks under differential privacy constraints.

Related papers

• Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data [0.0]
  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.
  arXiv  Detail & Related papers  (2026-07-08T14:33:00Z)
• Toward Individual Fairness Without Centralized Data: Selective Counterfactual Consistency for Vertical Federated Learning [16.277579974537996]
  We propose a server-centric framework for enforcing selective counterfactual consistency ( SCC-VFL) at the individual level in vertical federated learning (VFL)<n> SCC-VFL maintains or improves predictive accuracy while sharply reducing decision flip rates by up to 98% relative to strong baselines.<n>It also lowers attribute-inference attack success and improves robustness, demonstrating favorable utility-fairness-privacy trade-offs in realistic VFL deployments.
  arXiv  Detail & Related papers  (2026-05-08T01:50:06Z)
• Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning [21.950552296952623]
  Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes.<n>A common defense involves per-example $ell$ clipping before prototype to bound sensitivity, followed by isotropic noise to enforce Local Differential Privacy.<n>We propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFL.
  arXiv  Detail & Related papers  (2026-04-30T13:20:51Z)
• Managing Correlations in Data and Privacy Demand [4.855689194518906]
  We show that the standard HDP framework falls short when user data and privacy demands are allowed to be correlated.<n>We propose an alternate framework, Add-remove Heterogeneous Differential Privacy (AHDP), that jointly accounts for user data and privacy preference.
  arXiv  Detail & Related papers  (2025-09-02T22:03:13Z)
• Toward Fair Federated Learning under Demographic Disparities and Data Imbalance [8.444310568786408]
  Federated learning (FL) enables privacy-preserving collaboration across institutions.<n>We propose FedIDA, a framework-agnostic method that combines fairness-aware regularization with group-conditional oversampling.<n>We show that FedIDA consistently improves fairness while maintaining competitive predictive performance.
  arXiv  Detail & Related papers  (2025-05-14T11:22:54Z)
• Empirical Analysis of Privacy-Fairness-Accuracy Trade-offs in Federated Learning: A Step Towards Responsible AI [6.671649946926508]
  We present the first unified large-scale empirical study of privacy-fairness-utility trade-offs in Federated Learning (FL)<n>We compare fairness-awares with Differential Privacy (DP), Homomorphic Encryption (HE), and Secure Multi-Party Encryption (SMC)<n>We uncover unexpected interactions: DP mechanisms can negatively impact fairness, skew, and fairness-awares can inadvertently reduce privacy effectiveness.
  arXiv  Detail & Related papers  (2025-03-20T15:31:01Z)
• $(ε, δ)$-Differentially Private Partial Least Squares Regression [1.8666451604540077]
  We propose an $(epsilon, delta)$-differentially private PLS (edPLS) algorithm to ensure the privacy of the data underlying the model.<n> Experimental results demonstrate that edPLS effectively renders privacy attacks, aimed at recovering unique sources of variability in the training data.
  arXiv  Detail & Related papers  (2024-12-12T10:49:55Z)
• Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints [5.3595271893779906]
  We study federated learning for nonparametric regression in the context of distributed samples across different servers. Findings shed light on the tradeoff between statistical accuracy and privacy preservation.
  arXiv  Detail & Related papers  (2024-06-10T19:34:07Z)
• Privacy Amplification for the Gaussian Mechanism via Bounded Support [64.86780616066575]
  Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. We propose simple modifications of the Gaussian mechanism with bounded support, showing that they amplify privacy guarantees under data-dependent accounting.
  arXiv  Detail & Related papers  (2024-03-07T21:22:07Z)
• 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)
• Privacy Constrained Fairness Estimation for Decision Trees [2.9906966931843093]
  Measuring the fairness of any AI model requires the sensitive attributes of the individuals in the dataset. We propose a novel method, dubbed Privacy-Aware Fairness Estimation of Rules (PAFER) We show that using the Laplacian mechanism, the method is able to estimate SP with low error while guaranteeing the privacy of the individuals in the dataset with high certainty.
  arXiv  Detail & Related papers  (2023-12-13T14:54:48Z)
• PS-FedGAN: An Efficient Federated Learning Framework Based on Partially Shared Generative Adversarial Networks For Data Privacy [56.347786940414935]
  Federated Learning (FL) has emerged as an effective learning paradigm for distributed computation. This work proposes a novel FL framework that requires only partial GAN model sharing. Named as PS-FedGAN, this new framework enhances the GAN releasing and training mechanism to address heterogeneous data distributions.
  arXiv  Detail & Related papers  (2023-05-19T05:39:40Z)
• Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling [77.15766509677348]
  Conditional generative models often inherit spurious correlations from the training dataset. This can result in label-conditional distributions that are imbalanced with respect to another latent attribute. We propose a general two-step strategy to mitigate this issue.
  arXiv  Detail & Related papers  (2022-12-05T08:09:33Z)
• RDP-GAN: A R\'enyi-Differential Privacy based Generative Adversarial Network [75.81653258081435]
  Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection. However, when GANs are applied on sensitive or private training examples, such as medical or financial records, it is still probable to divulge individuals' sensitive and private information. We propose a R'enyi-differentially private-GAN (RDP-GAN), which achieves differential privacy (DP) in a GAN by carefully adding random noises on the value of the loss function during training.
  arXiv  Detail & Related papers  (2020-07-04T09:51:02Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

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.