Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning

• URL: http://arxiv.org/abs/2503.10945v2
• Date: Wed, 01 Oct 2025 19:57:59 GMT
• Title: Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
• Authors: Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis, Flavio P. Calmon, Jamie Hayes, Borja Balle, Antti Honkela,
• Abstract summary: Current practices for reporting the level of differential privacy for machine learning (ML) algorithms provide an incomplete and potentially misleading picture of the privacy guarantees.<n>We argue that using non-asymptotic Gaussian Differential Privacy (GDP) as the primary means of communicating DP guarantees in ML avoids these potential downsides.<n>We show how to provide non-asymptotic bounds on GDP using numerical accountants, and show that GDP can capture the entire privacy profile of DP-SGD and related algorithms with virtually no error, as quantified by the metric.
• Score: 27.52540933835594
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current practices for reporting the level of differential privacy (DP) protection for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture of the privacy guarantees. For instance, if only a single $(\varepsilon,\delta)$ is known about a mechanism, standard analyses show that there exist highly accurate inference attacks against training data records, when, in fact, such accurate attacks might not exist. In this position paper, we argue that using non-asymptotic Gaussian Differential Privacy (GDP) as the primary means of communicating DP guarantees in ML avoids these potential downsides. Using two recent developments in the DP literature: (i) open-source numerical accountants capable of computing the privacy profile and $f$-DP curves of DP-SGD to arbitrary accuracy, and (ii) a decision-theoretic metric over DP representations, we show how to provide non-asymptotic bounds on GDP using numerical accountants, and show that GDP can capture the entire privacy profile of DP-SGD and related algorithms with virtually no error, as quantified by the metric. To support our claims, we investigate the privacy profiles of state-of-the-art DP large-scale image classification, and the TopDown algorithm for the U.S. Decennial Census, observing that GDP fits their profiles remarkably well in all cases. We conclude with a discussion on the strengths and weaknesses of this approach, and discuss which other privacy mechanisms could benefit from GDP.

Related papers

• GPM: The Gaussian Pancake Mechanism for Planting Undetectable Backdoors in Differential Privacy [4.281902449361707]
  Several incidents of unintended privacy loss have occurred due to numerical issues and inappropriate configurations of Differential Privacy software.<n>We present the Gaussian pancake mechanism (GPM), a novel mechanism that is computationally indistinguishable from the widely used Gaussian mechanism (GM)<n>Unlike the unintentional privacy loss caused by GM's numerical issues, GPM is an adversarial yet undetectable backdoor attack against data privacy.
  arXiv  Detail & Related papers  (2025-09-28T12:14:06Z)
• Beyond the Worst Case: Extending Differential Privacy Guarantees to Realistic Adversaries [17.780319275883127]
  Differential Privacy is a family of definitions that bound the worst-case privacy leakage of a mechanism.<n>This work sheds light on what the worst-case guarantee of DP implies about the success of attackers that are more representative of real-world privacy risks.
  arXiv  Detail & Related papers  (2025-07-10T20:36:31Z)
• Machine Learning with Privacy for Protected Attributes [56.44253915927481]
  We refine the definition of differential privacy (DP) to create a more general and flexible framework that we call feature differential privacy (FDP)<n>Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary separation of protected and non-protected features.<n>We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available.
  arXiv  Detail & Related papers  (2025-06-24T17:53:28Z)
• How Private are DP-SGD Implementations? [61.19794019914523]
  We show that there can be a substantial gap between the privacy analysis when using the two types of batch sampling. Our result shows that there can be a substantial gap between the privacy analysis when using the two types of batch sampling.
  arXiv  Detail & Related papers  (2024-03-26T13:02:43Z)
• 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)
• Closed-Form Bounds for DP-SGD against Record-level Inference [18.85865832127335]
  We focus on the popular DP-SGD algorithm, and derive simple closed-form bounds. We obtain bounds for membership inference that match state-of-the-art techniques. We present a novel data-dependent bound against attribute inference.
  arXiv  Detail & Related papers  (2024-02-22T09:26:16Z)
• Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks? [19.21246519924815]
  For small privacy parameter $epsilon$, $epsilon$-differential privacy (DP) provides a strong worst-case guarantee. Existing DP theory cannot explain empirical findings. We propose a new privacy notion called practical membership privacy (PMP)
  arXiv  Detail & Related papers  (2024-02-14T19:31:45Z)
• Privacy Profiles for Private Selection [21.162924003105484]
  We work out an easy-to-use recipe that bounds privacy profiles of ReportNoisyMax and PrivateTuning using the privacy profiles of the base algorithms they corral. Our approach improves over all regimes of interest and leads to substantial benefits in end-to-end private learning experiments.
  arXiv  Detail & Related papers  (2024-02-09T08:31:46Z)
• Wasserstein Differential Privacy [4.112909937203119]
  We propose Wasserstein differential privacy (WDP), an alternative DP framework to measure the risk of privacy leakage. We show and prove that WDP has 13 excellent properties, which can be theoretical supports for the better performance of WDP. We derive a general privacy accounting method called Wasserstein accountant, which enables WDP to be applied in gradient descent scenarios.
  arXiv  Detail & Related papers  (2024-01-23T02:08:20Z)
• 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)
• 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)
• 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)
• Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent [69.14164921515949]
  We characterize privacy guarantees for individual examples when releasing models trained by DP-SGD. We find that most examples enjoy stronger privacy guarantees than the worst-case bound. This implies groups that are underserved in terms of model utility simultaneously experience weaker privacy guarantees.
  arXiv  Detail & Related papers  (2022-06-06T13:49:37Z)
• 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)
• DTGAN: Differential Private Training for Tabular GANs [6.174448419090292]
  We propose DTGAN, a novel conditional Wasserstein GAN that comes in two variants DTGAN_G and DTGAN_D. We rigorously evaluate the theoretical privacy guarantees offered by DP empirically against membership and attribute inference attacks. Our results on 3 datasets show that the DP-SGD framework is superior to PATE and that a DP discriminator is more optimal for training convergence.
  arXiv  Detail & Related papers  (2021-07-06T10:28:05Z)
• Smoothed Differential Privacy [55.415581832037084]
  Differential privacy (DP) is a widely-accepted and widely-applied notion of privacy based on worst-case analysis. In this paper, we propose a natural extension of DP following the worst average-case idea behind the celebrated smoothed analysis. We prove that any discrete mechanism with sampling procedures is more private than what DP predicts, while many continuous mechanisms with sampling procedures are still non-private under smoothed DP.
  arXiv  Detail & Related papers  (2021-07-04T06:55:45Z)

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.