Parallel Composition for Statistical Privacy

• URL: http://arxiv.org/abs/2602.09627v1
• Date: Tue, 10 Feb 2026 10:13:44 GMT
• Title: Parallel Composition for Statistical Privacy
• Authors: Dennis Breutigam, Rüdiger Reischuk,
• Abstract summary: A privacy mechanism is proposed that is based on subsampling and randomly partitioning the database to bound the dependency among queries.<n>These bounds show that in realistic application scenarios taking the entropy of distributions into account yields improvements of privacy and precision guarantees.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differential Privacy (DP) considers a scenario in which an adversary has almost complete information about the entries of a database. This worst-case assumption is likely to overestimate the privacy threat faced by an individual in practice. In contrast, Statistical Privacy (SP), as well as related notions such as noiseless privacy or limited background knowledge privacy, describe a setting in which the adversary knows the distribution of the database entries, but not their exact realizations. In this case, privacy analysis must account for the interaction between uncertainty induced by the entropy of the underlying distributions and privacy mechanisms that distort query answers, which can be highly non-trivial. This paper investigates this problem for multiple queries (composition). A privacy mechanism is proposed that is based on subsampling and randomly partitioning the database to bound the dependency among queries. This way for the first time, to the best of our knowledge, upper privacy bounds against limited adversaries are obtained without any further restriction on the database. These bounds show that in realistic application scenarios taking the entropy of distributions into account yields improvements of privacy and precision guarantees. We illustrate examples where for fixed privacy parameters and utility loss SP allows significantly more queries than DP.

Related papers

• MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation [54.410825977390274]
  Existing benchmarks to evaluate contextual privacy in LLM-agents primarily assess single-turn, low-complexity tasks.<n>We first present a benchmark - MAGPIE comprising 158 real-life high-stakes scenarios across 15 domains.<n>We then evaluate the current state-of-the-art LLMs on their understanding of contextually private data and their ability to collaborate without violating user privacy.
  arXiv  Detail & Related papers  (2025-06-25T18:04:25Z)
• Improving Statistical Privacy by Subsampling [0.0]
  A privacy mechanism often used is to take samples of the data for answering a query.<n>This paper proves precise bounds how much different methods of sampling increase privacy in the statistical setting.<n>For the DP setting tradeoff functions have been proposed as a finer measure for privacy compared to (epsilon,delta)-pairs.
  arXiv  Detail & Related papers  (2025-04-15T17:40:45Z)
• Enforcing Demographic Coherence: A Harms Aware Framework for Reasoning about Private Data Release [14.939460540040459]
  We introduce demographic coherence, a condition inspired by privacy attacks that we argue is necessary for data privacy.<n>Our framework focuses on confidence rated predictors, which can in turn be distilled from almost any data-informed process.<n>We prove that every differentially private data release is also demographically coherent, and that there are demographically coherent algorithms which are not differentially private.
  arXiv  Detail & Related papers  (2025-02-04T20:42:30Z)
• Statistical Privacy [0.0]
  This paper considers a situation where an adversary knows the distribution by which the database is generated, but no exact data of its entries.<n>We analyze in detail how the entropy of the distribution guarantes privacy for a large class of queries called property queries.
  arXiv  Detail & Related papers  (2025-01-22T14:13:44Z)
• Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy [55.357715095623554]
  Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. We propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification.
  arXiv  Detail & Related papers  (2024-10-24T03:39:55Z)
• A Statistical Viewpoint on Differential Privacy: Hypothesis Testing, Representation and Blackwell's Theorem [30.365274034429508]
  We argue that differential privacy can be considered a textitpure statistical concept. $f$-differential privacy is a unified framework for analyzing privacy bounds in data analysis and machine learning.
  arXiv  Detail & Related papers  (2024-09-14T23:47:22Z)
• Privately Answering Queries on Skewed Data via Per Record Differential Privacy [8.376475518184883]
  We propose a privacy formalism, per-record zero concentrated differential privacy (PzCDP)<n>Unlike other formalisms which provide different privacy losses to different records, PRzCDP's privacy loss depends explicitly on the confidential data.
  arXiv  Detail & Related papers  (2023-10-19T15:24:49Z)
• 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)
• 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)
• Algorithms with More Granular Differential Privacy Guarantees [65.3684804101664]
  We consider partial differential privacy (DP), which allows quantifying the privacy guarantee on a per-attribute basis. In this work, we study several basic data analysis and learning tasks, and design algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person.
  arXiv  Detail & Related papers  (2022-09-08T22:43:50Z)
• Privacy Amplification via Shuffling for Linear Contextual Bandits [51.94904361874446]
  We study the contextual linear bandit problem with differential privacy (DP) We show that it is possible to achieve a privacy/utility trade-off between JDP and LDP by leveraging the shuffle model of privacy. Our result shows that it is possible to obtain a tradeoff between JDP and LDP by leveraging the shuffle model while preserving local privacy.
  arXiv  Detail & Related papers  (2021-12-11T15:23:28Z)

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.