Accuracy-First Rényi Differential Privacy and Post-Processing Immunity

• URL: http://arxiv.org/abs/2509.22213v1
• Date: Fri, 26 Sep 2025 11:27:36 GMT
• Title: Accuracy-First Rényi Differential Privacy and Post-Processing Immunity
• Authors: Ossi Räisä, Antti Koskela, Antti Honkela,
• Abstract summary: Existing works on the accuracy-first perspective have neglected an important property of differential privacy known as post-processing immunity.<n>We propose a new definition based on R'enyi differential privacy that has post-processing immunity.
• Score: 11.418000446867135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The accuracy-first perspective of differential privacy addresses an important shortcoming by allowing a data analyst to adaptively adjust the quantitative privacy bound instead of sticking to a predetermined bound. Existing works on the accuracy-first perspective have neglected an important property of differential privacy known as post-processing immunity, which ensures that an adversary is not able to weaken the privacy guarantee by post-processing. We address this gap by determining which existing definitions in the accuracy-first perspective have post-processing immunity, and which do not. The only definition with post-processing immunity, pure ex-post privacy, lacks useful tools for practical problems, such as an ex-post analogue of the Gaussian mechanism, and an algorithm to check if accuracy on separate private validation set is high enough. To address this, we propose a new definition based on R\'enyi differential privacy that has post-processing immunity, and we develop basic theory and tools needed for practical applications. We demonstrate the practicality of our theory with an application to synthetic data generation, where our algorithm successfully adjusts the privacy bound until an accuracy threshold is met on a private validation dataset.

Related papers

• Privacy-Utility Tradeoffs in Quantum Information Processing [13.088625380700933]
  We study optimal tradeoffs for both generic and application-specific utility metrics when privacy is quantified by $(varepsilon,)$-quantum local differential privacy.<n>We derive a lower bound on the number of samples required to achieve a fixed accuracy guarantee with high probability.<n>We conclude by initiating the study of private classical shadows, which promise useful applications for private learning tasks.
  arXiv  Detail & Related papers  (2026-02-11T04:21:45Z)
• Conformal Prediction for Privacy-Preserving Machine Learning [83.88591755871734]
  Using AES-encrypted variants of the MNIST dataset, we demonstrate that Conformal Prediction methods remain effective even when applied directly in the encrypted domain.<n>Our work sets a foundation for principled uncertainty quantification in secure, privacy-aware learning systems.
  arXiv  Detail & Related papers  (2025-07-13T15:29:14Z)
• Privacy-Preserving Distributed Maximum Consensus Without Accuracy Loss [8.539683760001575]
  In distributed networks, calculating the maximum element is a fundamental task. Despite its importance, privacy in distributed maximum consensus has received limited attention in the literature. We propose a novel distributed optimization-based approach that preserves privacy without sacrificing accuracy.
  arXiv  Detail & Related papers  (2024-09-16T12:21:04Z)
• Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification [54.1447806347273]
  Amplification by subsampling is one of the main primitives in machine learning with differential privacy. We propose the first general framework for deriving mechanism-specific guarantees. We analyze how subsampling affects the privacy of groups of multiple users.
  arXiv  Detail & Related papers  (2024-03-07T19:36:05Z)
• Adaptive Privacy Composition for Accuracy-first Mechanisms [55.53725113597539]
  Noise reduction mechanisms produce increasingly accurate answers. Analysts only pay the privacy cost of the least noisy or most accurate answer released. There has yet to be any study on how ex-post private mechanisms compose. We develop privacy filters that allow an analyst to adaptively switch between differentially private and ex-post private mechanisms.
  arXiv  Detail & Related papers  (2023-06-24T00:33:34Z)
• A Randomized Approach for Tight Privacy Accounting [63.67296945525791]
  We propose a new differential privacy paradigm called estimate-verify-release (EVR) EVR paradigm first estimates the privacy parameter of a mechanism, then verifies whether it meets this guarantee, and finally releases the query output. Our empirical evaluation shows the newly proposed EVR paradigm improves the utility-privacy tradeoff for privacy-preserving machine learning.
  arXiv  Detail & Related papers  (2023-04-17T00:38:01Z)
• 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)
• Privacy Amplification via Shuffled Check-Ins [2.3333090554192615]
  We study a protocol for distributed computation called shuffled check-in. It achieves strong privacy guarantees without requiring any further trust assumptions beyond a trusted shuffler. We show that shuffled check-in achieves tight privacy guarantees through privacy amplification.
  arXiv  Detail & Related papers  (2022-06-07T09:55:15Z)
• Private measures, random walks, and synthetic data [7.5764890276775665]
  Differential privacy is a mathematical concept that provides an information-theoretic security guarantee. We develop a private measure from a data set that allows us to efficiently construct private synthetic data. A key ingredient in our construction is a new superregular random walk, whose joint distribution of steps is as regular as that of independent random variables.
  arXiv  Detail & Related papers  (2022-04-20T00:06:52Z)
• Private Prediction Sets [72.75711776601973]
  Machine learning systems need reliable uncertainty quantification and protection of individuals' privacy. We present a framework that treats these two desiderata jointly. We evaluate the method on large-scale computer vision datasets.
  arXiv  Detail & Related papers  (2021-02-11T18:59:11Z)
• Privacy Preserving Recalibration under Domain Shift [119.21243107946555]
  We introduce a framework that abstracts out the properties of recalibration problems under differential privacy constraints. We also design a novel recalibration algorithm, accuracy temperature scaling, that outperforms prior work on private datasets.
  arXiv  Detail & Related papers  (2020-08-21T18:43:37Z)

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.