Differentially Private Federated Learning

Ask about this topic

Overview

Differentially private federated learning studies how to train shared models across organizations or devices without exposing sensitive training data, using formal privacy guarantees to limit information revealed by the model or its updates. Common approaches clip and perturb gradients or client updates with calibrated noise, often alongside secure aggregation, privacy accounting, adaptive clipping, client selection, or parameter-efficient tuning such as LoRA. Work spans medical imaging, language models, intrusion detection, and other tasks with non-IID client data, where utility is assessed against privacy budgets and sometimes membership-inference or poisoning attacks. The central tension is that stronger privacy can reduce accuracy—especially for heterogeneous or rare data—while robustness, fairness, communication costs, and the precise scope of each privacy guarantee also need to be addressed together.

Latest papers

CardsList

65 papers5 papers in the last four weeks, down 55% on the four weeks before. 0.0% of all new papers.

  1. Towards Secure and Scalable Energy Theft Detection: A Federated Learning Approach for Resource-Constrained Smart Meters

    Feb 18, 2026Diego Labate, Dipanwita Thakur, Giancarlo FortinoFederated LearningAnomaly Detection

    DIMES, University of Calabria, Rende, Italy

  2. An Adaptive Differentially Private Federated Learning Framework

    Feb 6, 2026Jin Wang, Hui Ma, Yajun Zhang +4Non-IID Federated LearningDifferentially Private Federated Learning

    Xinjiang Key Laboratory of Intelligent Computing and Smart Applications, School of Software, Xinjiang University, Urumqi 830017, China · College of Geography and Remote Sensing Sciences, Xinjiang University, Urumqi, China · Jilin University, Changchun 130012, China

  3. A Privacy-Preserving Federated Learning Method for Heterogeneous Clients

    Nov 8, 2025Yusaku Negoya, Feifei Cui, Zilong Zhang +3Privacy-Preserving Federated LearningDifferentially Private Federated Learning

    Department of Computer and Network Engineering, The University of Electro-Communications, Tokyo, Japan · School of Computer Science and Technology, Hainan University, Haikou 570228, China. · Department of Electrical and Computer Engineering, University of Houston, Houston, TX, 77204, USA +1

  4. Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station

    Oct 27, 2025Hao Liang, Haifeng Wen, Kaishun Wu +2Personalized Differential PrivacyOver-the-Air Federated Learning

    IoT Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China · Department of ECE, The Hong Kong University of Science and Technology, HK SAR

  5. Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI

    May 28, 2025Santhosh Parampottupadam, Melih Coşğun, Sarthak Pati +7Federated Learning AggregationDifferentially Private Stochastic Gradient Descent

    German Cancer Research Center (DKFZ), Division of Medical Image Computing, Heidelberg, Germany · Department of Computer Engineering, Bilkent University, Universiteler 06800 Çankaya/Ankara, Türkiye · Medical Research Group, MLCommons, San Francisco, CA, USA +2