PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning

• URL: http://arxiv.org/abs/2603.24003v1
• Date: Wed, 25 Mar 2026 07:06:33 GMT
• Title: PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning
• Abstract summary: PAC-DP is a personalized Adaptive Clipping framework for federated learning.<n>We show that PAC-DP surpasses conventional fixed-threshold approaches under matched privacy budgets.
• Score: 16.9867659381048
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differential privacy (DP) is crucial for safeguarding sensitive client information in federated learning (FL), yet traditional DP-FL methods rely predominantly on fixed gradient clipping thresholds. Such static clipping neglects significant client heterogeneity and varying privacy sensitivities, which may lead to an unfavorable privacy-utility trade-off. In this paper, we propose PAC-DP, a Personalized Adaptive Clipping framework for federated learning under record-level local differential privacy. PAC-DP introduces a Simulation-CurveFitting approach leveraging a server-hosted public proxy dataset to learn an effective mapping between personalized privacy budgets epsilon and gradient clipping thresholds C, which is then deployed online with a lightweight round-wise schedule. This design enables budget-conditioned threshold selection while avoiding data-dependent tuning during training. We provide theoretical analyses establishing convergence guarantees under the per-example clipping and Gaussian perturbation mechanism and a reproducible privacy accounting procedure. Extensive evaluations on multiple FL benchmarks show that PAC-DP surpasses conventional fixed-threshold approaches under matched privacy budgets, improving accuracy by up to 26% and accelerating convergence by up to 45.5% in our evaluated settings.

Related papers

• DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models [25.94292199187493]
  Federated learning (FL) enables the collaborative training of large-scale language models across edge devices while keeping user data on-device.<n>DP-SGD mitigates this risk by clipping each client's contribution to a threshold $C$ and adding noise proportional to $C$.<n>We introduce DP-LAC, a method that first estimates an initial clipping threshold within an order of magnitude of the optimum using private histogram estimation.<n> Empirical results show that DP-LAC outperforms both state-of-the-art adaptive clipping methods and vanilla DP-SGD, achieving an average accuracy gain of $6.6%$
  arXiv  Detail & Related papers  (2026-05-11T09:32:21Z)
• Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning [21.950552296952623]
  Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes.<n>A common defense involves per-example $ell$ clipping before prototype to bound sensitivity, followed by isotropic noise to enforce Local Differential Privacy.<n>We propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFL.
  arXiv  Detail & Related papers  (2026-04-30T13:20:51Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise [0.0]
  We explore differentially private synthetic data generation in a decentralized-data setting.<n>We build on the recently proposed Differentially Private Class-Centric Data Aggregation.
  arXiv  Detail & Related papers  (2025-09-12T16:18:35Z)
• FedRE: Robust and Effective Federated Learning with Privacy Preference [20.969342596181246]
  Federated Learning (FL) employs gradient aggregation at the server for distributed training to prevent the privacy leakage of raw data.<n>Private information can still be divulged through the analysis of uploaded gradients from clients.<n>Existing methods fail to take practical issues into account by merely perturbing each sample with the same mechanism.
  arXiv  Detail & Related papers  (2025-05-08T01:50:27Z)
• Multi-Objective Optimization for Privacy-Utility Balance in Differentially Private Federated Learning [12.278668095136098]
  Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data.<n>We propose an adaptive clipping mechanism that dynamically adjusts the clipping norm using a multi-objective optimization framework.<n>Our results show that adaptive clipping consistently outperforms fixed-clipping baselines, achieving improved accuracy under the same privacy constraints.
  arXiv  Detail & Related papers  (2025-03-27T04:57:05Z)
• 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)
• FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations [53.268801169075836]
  We propose FedLAP-DP, a novel privacy-preserving approach for federated learning. A formal privacy analysis demonstrates that FedLAP-DP incurs the same privacy costs as typical gradient-sharing schemes. Our approach presents a faster convergence speed compared to typical gradient-sharing methods.
  arXiv  Detail & Related papers  (2023-02-02T12:56:46Z)
• Gradient-Leakage Resilient Federated Learning [8.945356237213007]
  Federated learning(FL) is an emerging distributed learning paradigm with default client privacy. Recent studies reveal that gradient leakages in FL may compromise the privacy of client training data. This paper presents a gradient leakage resilient approach to privacy-preserving federated learning with per training example-based client differential privacy.
  arXiv  Detail & Related papers  (2021-07-02T15:51:07Z)
• Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy [67.4471689755097]
  This paper empirically demonstrates that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity. We provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates.
  arXiv  Detail & Related papers  (2021-06-25T14:47:19Z)
• Private Reinforcement Learning with PAC and Regret Guarantees [69.4202374491817]
  We design privacy preserving exploration policies for episodic reinforcement learning (RL) We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP) We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee.
  arXiv  Detail & Related papers  (2020-09-18T20:18:35Z)
• Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization [27.243322019117144]
  Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. We propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee.
  arXiv  Detail & Related papers  (2020-08-01T20:22:57Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

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.