Differential Privacy via Distributionally Robust Optimization

• URL: http://arxiv.org/abs/2304.12681v2
• Date: Thu, 23 May 2024 15:48:56 GMT
• Title: Differential Privacy via Distributionally Robust Optimization
• Authors: Aras Selvi, Huikang Liu, Wolfram Wiesemann,
• Abstract summary: We develop a class of mechanisms that enjoy non-asymptotic and unconditional optimality guarantees. Our upper (primal) bounds correspond to implementable perturbations whose suboptimality can be bounded by our lower (dual) bounds. Our numerical experiments demonstrate that our perturbations can outperform the previously best results from the literature on artificial as well as standard benchmark problems.
• Score: 8.409434654561789
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, differential privacy has emerged as the de facto standard for sharing statistics of datasets while limiting the disclosure of private information about the involved individuals. This is achieved by randomly perturbing the statistics to be published, which in turn leads to a privacy-accuracy trade-off: larger perturbations provide stronger privacy guarantees, but they result in less accurate statistics that offer lower utility to the recipients. Of particular interest are therefore optimal mechanisms that provide the highest accuracy for a pre-selected level of privacy. To date, work in this area has focused on specifying families of perturbations a priori and subsequently proving their asymptotic and/or best-in-class optimality. In this paper, we develop a class of mechanisms that enjoy non-asymptotic and unconditional optimality guarantees. To this end, we formulate the mechanism design problem as an infinite-dimensional distributionally robust optimization problem. We show that the problem affords a strong dual, and we exploit this duality to develop converging hierarchies of finite-dimensional upper and lower bounding problems. Our upper (primal) bounds correspond to implementable perturbations whose suboptimality can be bounded by our lower (dual) bounds. Both bounding problems can be solved within seconds via cutting plane techniques that exploit the inherent problem structure. Our numerical experiments demonstrate that our perturbations can outperform the previously best results from the literature on artificial as well as standard benchmark problems.

Related papers

• Private Optimal Inventory Policy Learning for Feature-based Newsvendor with Unknown Demand [13.594765018457904]
  This paper introduces a novel approach to estimate a privacy-preserving optimal inventory policy within the f-differential privacy framework. We develop a clipped noisy gradient descent algorithm based on convolution smoothing for optimal inventory estimation. Our numerical experiments demonstrate that the proposed new method can achieve desirable privacy protection with a marginal increase in cost.
  arXiv  Detail & Related papers  (2024-04-23T19:15:43Z)
• Double Duality: Variational Primal-Dual Policy Optimization for Constrained Reinforcement Learning [132.7040981721302]
  We study the Constrained Convex Decision Process (MDP), where the goal is to minimize a convex functional of the visitation measure. Design algorithms for a constrained convex MDP faces several challenges, including handling the large state space.
  arXiv  Detail & Related papers  (2024-02-16T16:35:18Z)
• Bounded and Unbiased Composite Differential Privacy [25.427802467876248]
  The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between two neighboring databases. Existing solutions attempt to address this issue by employing post-processing or truncation techniques. We propose a novel differentially private mechanism which uses a composite probability density function to generate bounded and unbiased outputs.
  arXiv  Detail & Related papers  (2023-11-04T04:43:47Z)
• Optimal Private Discrete Distribution Estimation with One-bit Communication [63.413106413939836]
  We consider a private discrete distribution estimation problem with one-bit communication constraint. We characterize the first-orders of the worst-case trade-off under the one-bit communication constraint. These results demonstrate the optimal dependence of the privacy-utility trade-off under the one-bit communication constraint.
  arXiv  Detail & Related papers  (2023-10-17T05:21:19Z)
• Generating Private Synthetic Data with Genetic Algorithms [29.756119782419955]
  We study the problem of efficiently generating differentially private synthetic data that approximates the statistical properties of an underlying sensitive dataset. We propose Private-GSD, a private genetic algorithm based on zeroth-order optimizations that do not require modifying the original objective. We show that Private-GSD outperforms the state-of-the-art methods on non-differential queries while matching accuracy in approximating differentiable ones.
  arXiv  Detail & Related papers  (2023-06-05T21:19:37Z)
• On User-Level Private Convex Optimization [59.75368670035683]
  We introduce a new mechanism for convex optimization (SCO) with user-level differential privacy guarantees. Our mechanism does not require any smoothness assumptions on the loss. Our bounds are the first where the minimum number of users needed for user-level privacy has no dependence on the dimension.
  arXiv  Detail & Related papers  (2023-05-08T17:47:28Z)
• Decentralized Nonconvex Optimization with Guaranteed Privacy and Accuracy [34.24521534464185]
  Privacy protection and nonity are two challenging problems in decentralized optimization learning sensitive data. We propose an algorithm that allows both privacy protection and avoidance. The algorithm is efficient in both communication and computation.
  arXiv  Detail & Related papers  (2022-12-14T22:36:13Z)
• DP2-Pub: Differentially Private High-Dimensional Data Publication with Invariant Post Randomization [58.155151571362914]
  We propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases. splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable privacy budget. We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy.
  arXiv  Detail & Related papers  (2022-08-24T17:52:43Z)
• Decentralized Stochastic Optimization with Inherent Privacy Protection [103.62463469366557]
  Decentralized optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing. Since involved data, privacy protection has become an increasingly pressing need in the implementation of decentralized optimization algorithms.
  arXiv  Detail & Related papers  (2022-05-08T14:38:23Z)
• Bilevel Optimization for Differentially Private Optimization in Energy Systems [53.806512366696275]
  This paper studies how to apply differential privacy to constrained optimization problems whose inputs are sensitive. The paper shows that, under a natural assumption, a bilevel model can be solved efficiently for large-scale nonlinear optimization problems.
  arXiv  Detail & Related papers  (2020-01-26T20:15:28Z)

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.