$α$-Wasserstein Mechanism for Rényi Pufferfish Privacy

• URL: http://arxiv.org/abs/2605.05723v1
• Date: Thu, 07 May 2026 06:12:18 GMT
• Title: $α$-Wasserstein Mechanism for Rényi Pufferfish Privacy
• Abstract summary: This paper introduces the $$-Wasserstein mechanism for achieving Rényi Pufferfish Privacy.<n>We demonstrate that the scale parameter of the Laplace mechanism can be calibrated via an upper bound on the $W_$ metric to satisfy $(, )$-Rényi Pufferfish Privacy for $in (1, infty)$.
• Score: 9.365672064609344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper introduces the $α$-Wasserstein mechanism for achieving Rényi Pufferfish Privacy using Laplace and Gaussian noise. By leveraging Hölder's inequality, we demonstrate that the scale parameter of the Laplace mechanism can be calibrated via an upper bound on the $W_α$ metric to satisfy $(α, ε)$-Rényi Pufferfish Privacy for $α\in (1, \infty]$. We show that at the limit $α= \infty$, this framework recovers the established $W_\infty$ mechanism for $ε$-pufferfish privacy. This result is subsequently extended to the exponential mechanism. Furthermore, we propose a $W_α$ mechanism for Gaussian noise for $α\in (1, \infty)$, demonstrating that it generalizes existing results within the Rényi Differential Privacy framework. Experimental evaluations reveal that our $α$-Wasserstein mechanism significantly reduces noise power compared to the conventional $W_\infty$-based approach, with the Gaussian mechanism providing superior utility over the Laplace mechanism. Notably, the mechanisms derived in this work achieve exact $(α, ε)$-Rényi Pufferfish Privacy without requiring additional relaxations, such as $δ$-approximations.

Related papers

• Asymptotic Optimality of the High-Dimensional Gaussian Mechanism and Improved Low-Dimensional Mechanisms for Differential Privacy [51.25798439950639]
  We show that no additive-noise mechanism can improve on the Gaussian mechanism's privacy--utility tradeoff for the strong privacy settings typically used.<n>We develop a new family of emphSpherical Generalized Gamma DP mechanisms, which contains both the Gaussian mechanism and the recently studied $ell$ mechanism.
  arXiv  Detail & Related papers  (2026-06-07T15:33:30Z)
• Hidden-State Privacy Has an Empty Middle [51.56484100374058]
  We prove a complementary Fisher-ball lower bound: every full-rank Gaussian release at $O(1)$ Fisher utility admits a direction whose Mahalanobis signal grows linearly in hidden width.<n>A split-memory transformer trained from scratch reaches $G_mathrmMah in [20, 33]$ at 90M and maintains a $6$--$24times$ advantage over same-budget GPT baselines from 30M to 1B at a fixed-token language loss penalty.
  arXiv  Detail & Related papers  (2026-05-21T20:12:09Z)
• LoRA and Privacy: When Random Projections Help (and When They Don't) [55.65932772290123]
  We introduce the (Wishart) projection mechanism, a randomized map of the form $S mapsto M f(S)$ with $M sim W_d (1/r I_d, r)$ and study its differential privacy properties.<n>For vector-valued queries $f$, we prove non-asymptotic DP guarantees without any additive noise, showing that Wishart randomness alone can suffice.<n>For matrix-valued queries, however, we establish a sharp negative result: in the noise-free setting, the mechanism is not DP, and we demonstrate its vulnerability.
  arXiv  Detail & Related papers  (2026-01-29T13:43:37Z)
• Noise Reduction for Pufferfish Privacy: A Practical Noise Calibration Method [39.60741423066451]
  This paper builds on the existing $1$-Wasserstein (Kantorovich) mechanism by alleviating the existing overly strict condition that leads to excessive noise.<n>We prove that a strict noise reduction by our approach always exists compared to $1$-Wasserstein mechanism for all privacy budgets $$ and prior beliefs.<n> Experimental results on three real-world datasets demonstrate $47%$ to $87%$ improvement in data utility.
  arXiv  Detail & Related papers  (2026-01-10T02:01:45Z)
• Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning [49.66162382667325]
  We investigate the Generalized Gaussian mechanism, which samples the additive noise term $x$ with probability proportional to $e-frac| x |sigmabeta $ for some $beta geq 1$.<n>We show that privacy accounting for the GG Mechanism and its variants is independent, which substantially improves computational costs of privacy accounting.
  arXiv  Detail & Related papers  (2025-06-14T15:49:25Z)
• Approximate Differential Privacy of the $\ell_2$ Mechanism [52.61055173572399]
  We study the $ell$ mechanism for computing a $d$-dimensional statistic with bounded $ell$ sensitivity under approximate differential privacy.<n>Across a range of privacy parameters, we find that the $ell$ mechanism obtains lower error than the Laplace and Gaussian mechanisms.
  arXiv  Detail & Related papers  (2025-02-21T20:56:34Z)
• Count on Your Elders: Laplace vs Gaussian Noise [9.546521474972485]
  We argue that Laplace noise may in fact be preferable to Gaussian noise in many settings. We show that the noise added by the Gaussian mechanism can always be replaced by Laplace noise of comparable variance. This challenges the conventional wisdom that Gaussian noise should be used for high-dimensional noise.
  arXiv  Detail & Related papers  (2024-08-13T16:36:33Z)
• Some Constructions of Private, Efficient, and Optimal $K$-Norm and Elliptic Gaussian Noise [54.34628844260993]
  Differentially private computation often begins with a bound on some $d$-dimensional statistic's sensitivity. For pure differential privacy, the $K$-norm mechanism can improve on this approach using a norm tailored to the statistic's sensitivity space. This paper solves both problems for the simple statistics of sum, count, and vote.
  arXiv  Detail & Related papers  (2023-09-27T17:09:36Z)
• Faster Privacy Accounting via Evolving Discretization [54.32252900997422]
  We introduce a new algorithm for numerical composition of privacy random variables. Our algorithm achieves a running time and memory usage of $mathrmpolylog(k)$ for the task of self-composing a mechanism.
  arXiv  Detail & Related papers  (2022-07-10T04:25:37Z)
• Differential privacy for symmetric log-concave mechanisms [0.0]
  Adding random noise to database query results is an important tool for achieving privacy. We provide a sufficient and necessary condition for $(epsilon, delta)$-differential privacy for all symmetric and log-concave noise densities.
  arXiv  Detail & Related papers  (2022-02-23T10:20:29Z)
• Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling [49.43288037509783]
  We show that random shuffling amplifies differential privacy guarantees of locally randomized data. Our result is based on a new approach that is simpler than previous work and extends to approximate differential privacy with nearly the same guarantees.
  arXiv  Detail & Related papers  (2020-12-23T17:07:26Z)
• A bounded-noise mechanism for differential privacy [3.9596068699962323]
  We output an approximation of the average $frac1nsum_i=1n vecx(i)$ of vectors $vecx(i) in [0,1]k$, while preserving the privacy with respect to any $vecx(i)$. We present an $(epsilon,delta)$-private mechanism with optimal $ell_infty$ error for most values of $delta$.
  arXiv  Detail & Related papers  (2020-12-07T16:03:21Z)

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.