When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence

• URL: http://arxiv.org/abs/2603.19040v1
• Date: Thu, 19 Mar 2026 15:38:06 GMT
• Title: When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
• Abstract summary: We present a comprehensive analysis of privacy and convergence for Differentially private wireless learning (DPWFL)<n>We derive an explicit privacy-utility trade-off and Numerical results validate our findings.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Differentially private wireless federated learning (DPWFL) is a promising framework for protecting sensitive user data. However, foundational questions on how to precisely characterize privacy loss remain open, and existing work is further limited by convergence analyses that rely on restrictive convexity assumptions or ignore the effect of gradient clipping. To overcome these issues, we present a comprehensive analysis of privacy and convergence for DPWFL with general smooth non-convex loss objectives. Our analysis explicitly incorporates both device selection and mini-batch sampling, and shows that the privacy loss can converge to a constant rather than diverge with the number of iterations. Moreover, we establish convergence guarantees with gradient clipping and derive an explicit privacy-utility trade-off. Numerical results validate our theoretical findings.

Related papers

• Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy [5.19945480121051]
  Existing private approaches often rely on data splitting, reducing the effective sample size.<n>We propose a full-data privacy-preserving conformal prediction framework that avoids splitting.<n>We show that a generic differential privacy guarantee yields a universal coverage floor, yet cannot generally recover the nominal $1-$ level.
  arXiv  Detail & Related papers  (2026-03-08T08:25:16Z)
• Subgraph Federated Learning via Spectral Methods [52.40322201034717]
  FedLap is a novel framework that captures inter-node dependencies while ensuring privacy and scalability.<n>We provide a formal analysis of the privacy of FedLap, demonstrating that it preserves privacy.
  arXiv  Detail & Related papers  (2025-10-29T16:22:32Z)
• An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses [26.98562734120675]
  We provide rigorous privacy and utility characterization for Differentially Private Gradient Descent.<n>We show that for DPSGD with a bounded domain, the privacy loss can still converge without the convexity assumption.
  arXiv  Detail & Related papers  (2025-02-25T02:05:41Z)
• Convergent Differential Privacy Analysis for General Federated Learning: the $f$-DP Perspective [57.35402286842029]
  Federated learning (FL) is an efficient collaborative training paradigm with a focus on local privacy. differential privacy (DP) is a classical approach to capture and ensure the reliability of private protections.
  arXiv  Detail & Related papers  (2024-08-28T08:22:21Z)
• Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints [5.3595271893779906]
  We study federated learning for nonparametric regression in the context of distributed samples across different servers. Findings shed light on the tradeoff between statistical accuracy and privacy preservation.
  arXiv  Detail & Related papers  (2024-06-10T19:34:07Z)
• 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)
• Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks [72.51255282371805]
  We prove a privacy bound for the KL divergence between model distributions on worst-case neighboring datasets. We find that this KL privacy bound is largely determined by the expected squared gradient norm relative to model parameters during training.
  arXiv  Detail & Related papers  (2023-10-31T16:13:22Z)
• Differentially Private Wireless Federated Learning Using Orthogonal Sequences [56.52483669820023]
  We propose a privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS. We prove that FLORAS offers both item-level and client-level differential privacy guarantees. A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels.
  arXiv  Detail & Related papers  (2023-06-14T06:35:10Z)
• Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses [4.68299658663016]
  The Noisy-SGD algorithm is widely used for privately training machine learning models. Recent findings have shown that if the internal state remains hidden, then the privacy loss might remain bounded. We address this problem for DP-SGD, a popular variant of Noisy-SGD that incorporates gradient clipping to limit the impact of individual samples on the training process.
  arXiv  Detail & Related papers  (2023-05-17T02:25:56Z)
• On the Query Complexity of Training Data Reconstruction in Private Learning [0.0]
  We analyze the number of queries that a whitebox adversary needs to make to a private learner in order to reconstruct its training data. For $(epsilon, delta)$ DP learners with training data drawn from any arbitrary compact metric space, we provide the emphfirst known lower bounds on the adversary's query complexity.
  arXiv  Detail & Related papers  (2023-03-29T00:49:38Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• On the Statistical Complexity of Estimation and Testing under Privacy Constraints [17.04261371990489]
  We show how to characterize the power of a statistical test under differential privacy in a plug-and-play fashion. We show that maintaining privacy results in a noticeable reduction in performance only when the level of privacy protection is very high. Finally, we demonstrate that the DP-SGLD algorithm, a private convex solver, can be employed for maximum likelihood estimation with a high degree of confidence.
  arXiv  Detail & Related papers  (2022-10-05T12:55:53Z)
• Robustness Threats of Differential Privacy [70.818129585404]
  We experimentally demonstrate that networks, trained with differential privacy, in some settings might be even more vulnerable in comparison to non-private versions. We study how the main ingredients of differentially private neural networks training, such as gradient clipping and noise addition, affect the robustness of the model.
  arXiv  Detail & Related papers  (2020-12-14T18:59:24Z)

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.