paper-with-me

홈 › Papers

Limits of Personalizing Differential Privacy Budgets

2026-05-13 · Edwige Cyffers, Juba Ziani arxiv

A key technical difficulty in differential privacy is selecting a privacy budget that satisfies privacy requirements while maximizing utility. A natural and well-studied workaround is to use personalized privacy budgets, which may differ across agents. In this paper, we show that personalized budgets come with major limitations and that for mean estimation, the dominant factor is not full personalization, but rather choosing the right effective privacy budget. This can be achieved through a simple thresholding operator that we describe. Compared with this thresholding baseline, the gains obtained by fully personalized mechanisms are limited. In particular, we precisely quantify the constant-factor improvement in settings with mixed private and public datasets and in private datasets with two levels of privacy requirements. We also establish upper bounds and identify regimes of maximal gain for arbitrary privacy requirements.

📄 PDF Abstract BibTeX arXiv:2605.13503

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Graph Structure Learning with Privacy Guarantees for Open Graph Data

2025-07-25 · Muhao Guo, Jiaqi Wu, Yizheng Liao, Wenke Lee 외 arxiv

Publishing open graph data while preserving individual privacy remains challenging when data publishers and data users are distinct entities. Although differential privacy (DP) provides rigorous guarantees, most existing…

Graph structure learning

Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning

2026-05-04 · Judith Sáinz-Pardo Díaz, Álvaro López García arxiv

The growing development of artificial intelligence based solutions, together with privacy legislation, has driven the rise of the so-called privacy preserving machine learning architectures, such as federated learning. W…

Federated Learning

Wasserstein Differential Privacy

2024-01-23 · Chengyi Yang, Jiayin Qi, Aimin Zhou

Differential privacy (DP) has achieved remarkable results in the field of privacy-preserving machine learning. However, existing DP frameworks do not satisfy all the conditions for becoming metrics, which prevents them f…

Privacy Preserving

Differentially Private Federated Learning With Time-Adaptive Privacy Spending

2025-02-25 · Shahrzad Kiani, Nupur Kulkarni, Adam Dziedzic, Stark Draper 외

Federated learning (FL) with differential privacy (DP) provides a framework for collaborative machine learning, enabling clients to train a shared model while adhering to strict privacy constraints. The framework allows …

Federated Learning

Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation

2023-09-06 · Xiaochen Zhu, Vincent Y. F. Tan, Xiaokui Xiao

Graph neural networks (GNNs) have gained an increasing amount of popularity due to their superior capability in learning node embeddings for various graph inference tasks, but training them can raise privacy concerns. To…