Meeting Utility Constraints in Differential Privacy: A Privacy-Boosting Approach
- URL: http://arxiv.org/abs/2412.10612v1
- Date: Fri, 13 Dec 2024 23:34:30 GMT
- Title: Meeting Utility Constraints in Differential Privacy: A Privacy-Boosting Approach
- Authors: Bo Jiang, Wanrong Zhang, Donghang Lu, Jian Du, Sagar Sharma, Qiang Yan,
- Abstract summary: We propose a privacy-boosting framework that is compatible with most noise-adding DP mechanisms.
Our framework enhances the likelihood of outputs falling within a preferred subset of the support to meet utility requirements.
We show that our framework achieves lower privacy loss than standard DP mechanisms under utility constraints.
- Score: 7.970280110429423
- License:
- Abstract: Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we propose a privacy-boosting framework that is compatible with most noise-adding DP mechanisms. Our framework enhances the likelihood of outputs falling within a preferred subset of the support to meet utility requirements while enlarging the overall variance to reduce privacy leakage. We characterize the privacy loss distribution of our framework and present the privacy profile formulation for $(\epsilon,\delta)$-DP and R\'enyi DP (RDP) guarantees. We study special cases involving data-dependent and data-independent utility formulations. Through extensive experiments, we demonstrate that our framework achieves lower privacy loss than standard DP mechanisms under utility constraints. Notably, our approach is particularly effective in reducing privacy loss with large query sensitivity relative to the true answer, offering a more practical and flexible approach to designing differentially private mechanisms that meet specific utility constraints.
Related papers
- 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) - Private Language Models via Truncated Laplacian Mechanism [18.77713904999236]
We propose a novel private embedding method called the high dimensional truncated Laplacian mechanism.
We show that our method has a lower variance compared to the previous private word embedding methods.
Remarkably, even in the high privacy regime, our approach only incurs a slight decrease in utility compared to the non-private scenario.
arXiv Detail & Related papers (2024-10-10T15:25:02Z) - Differential Confounding Privacy and Inverse Composition [32.85314813605347]
We introduce Differential Confounding Privacy (DCP), a framework that generalizes Differential Privacy (DP)
We show that DCP mechanisms retain privacy guarantees under composition, but they lack the graceful compositional properties of DP.
We propose an Inverse Composition (IC) framework, where a leader-follower model optimally designs a privacy strategy to achieve target guarantees without relying on worst-case privacy proofs.
arXiv Detail & Related papers (2024-08-21T21:45:13Z) - Provable Privacy with Non-Private Pre-Processing [56.770023668379615]
We propose a general framework to evaluate the additional privacy cost incurred by non-private data-dependent pre-processing algorithms.
Our framework establishes upper bounds on the overall privacy guarantees by utilising two new technical notions.
arXiv Detail & Related papers (2024-03-19T17:54:49Z) - 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) - 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) - 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)
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.