INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy

• URL: http://arxiv.org/abs/2605.07930v1
• Date: Fri, 08 May 2026 16:04:09 GMT
• Title: INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
• Abstract summary: Differential privacy (DP) is widely employed in machine learning to protect confidential or sensitive training data from being revealed.<n>We propose the INO-SGD algorithm, which strategically down-weights data within each batch to improve performance on the more private data.
• Score: 49.094769650817796
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Differential privacy (DP) is widely employed in machine learning to protect confidential or sensitive training data from being revealed. As data owners gain greater control over their data due to personal data ownership, they are more likely to set their own privacy requirements, necessitating individualized DP (IDP) to fulfil such requests. In particular, owners of data from more sensitive subsets, such as positive cases of stigmatized diseases, likely set stronger privacy requirements, as leakage of such data could incur more serious societal impact. However, existing IDP algorithms induce a critical utility imbalance problem: Data from owners with stronger privacy requirements may be severely underrepresented in the trained model, resulting in poorer performance on similar data from subsequent users during deployment. In this paper, we analyze this problem and propose the INO-SGD algorithm, which strategically down-weights data within each batch to improve performance on the more private data across all iterations. Notably, our algorithm is specially designed to satisfy IDP, while existing techniques addressing utility imbalance neither satisfy IDP nor can be easily adapted to do so. Lastly, we demonstrate the empirical feasibility of our approach.

Related papers

• How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy [52.00934156883483]
  Differential Privacy (DP) is a framework for reasoning about and limiting information leakage.<n>Differentially Private Synthetic data refers to synthetic data that preserves the overall trends of source data.
  arXiv  Detail & Related papers  (2025-12-02T21:14:39Z)
• Improving Noise Efficiency in Privacy-preserving Dataset Distillation [59.57846442477106]
  We introduce a novel framework that decouples sampling from optimization for better convergence and improves signal quality.<n>On CIFAR-10, our method achieves a textbf10.0% improvement with 50 images per class and textbf8.3% increase with just textbfone-fifth the distilled set size of previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-03T13:15:52Z)
• Optimal Allocation of Privacy Budget on Hierarchical Data Release [48.96399034594329]
  This paper addresses the problem of optimal privacy budget allocation for hierarchical data release.<n>It aims to maximize data utility subject to a total privacy budget while considering the inherent trade-offs between data granularity and privacy loss.
  arXiv  Detail & Related papers  (2025-05-16T05:25:11Z)
• DP-CDA: An Algorithm for Enhanced Privacy Preservation in Dataset Synthesis Through Randomized Mixing [0.8739101659113155]
  We introduce an effective data publishing algorithm emphDP-CDA.<n>Our proposed algorithm generates synthetic datasets by randomly mixing data in a class-specific manner, and inducing carefully-tuned randomness to ensure privacy guarantees.<n>Our results indicate that synthetic datasets produced using the DP-CDA can achieve superior utility compared to those generated by traditional data publishing algorithms, even when subject to the same privacy requirements.
  arXiv  Detail & Related papers  (2024-11-25T06:14:06Z)
• 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 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)
• Conciliating Privacy and Utility in Data Releases via Individual Differential Privacy and Microaggregation [4.287502453001108]
  $epsilon$-Differential privacy (DP) is a well-known privacy model that offers strong privacy guarantees. We propose $epsilon$-individual differential privacy (iDP), which causes less data distortion while providing the same protection as DP to subjects. We report on experiments that show how our approach can provide strong privacy (small $epsilon$) while yielding protected data that do not significantly degrade the accuracy of secondary data analysis.
  arXiv  Detail & Related papers  (2023-12-21T10:23:18Z)
• 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)
• How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
  We study the connection between the per-subject norm in DP neural networks and individual privacy loss. We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
  arXiv  Detail & Related papers  (2022-11-18T11:39:03Z)
• 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)
• P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model [23.91327154831855]
  This paper proposes privacy-preserving phased generative model (P3GM) for releasing sensitive data. P3GM employs the two-phase learning process to make it robust against the noise, and to increase learning efficiency. Compared with the state-of-the-art methods, our generated samples look fewer noises and closer to the original data in terms of data diversity.
  arXiv  Detail & Related papers  (2020-06-22T09:47:54Z)

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.