mlsanityData to 7 Oct 2026

Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise

arXiv 2211.15893 ↗First posted 29 Nov 2022cs.LG cs.CR cs.DCcited by 12

Not on the map. Why?

Abstract (arXiv)

Federated learning seeks to address the issue of isolated data islands by making clients disclose only their local training models. However, it was demonstrated that private information could still be inferred by analyzing local model parameters, such as deep neural network model weights. Recently, differential privacy has been applied to federated learning to protect data privacy, but the noise added may degrade the learning performance much. Typically, in previous work, training parameters were clipped equally and noises were added uniformly. The heterogeneity and convergence of training parameters were simply not considered. In this paper, we propose a differentially private scheme for federated learning with adaptive noise (Adap DP-FL). Specifically, due to the gradient heterogeneity, we conduct adaptive gradient clipping for different clients and different rounds; due to the gradient convergence, we add decreasing noises accordingly. Extensive experiments on real-world datasets demonstrate that our Adap DP-FL outperforms previous methods significantly.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

25 of 34 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2017Renyi Differential Privacycited by 643
  6. 2018Federated Learning for Mobile Keyboard Predictioncited by 565
  7. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  8. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  9. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  10. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  11. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  12. 2015Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decompositioncited by 241
13 more
  1. 2019Differentially Private Learning with Adaptive Clippingcited by 218
  2. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  3. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 199
  4. 2017Machine Learning Models that Remember Too Muchcited by 165
  5. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  6. 2019AdaCliP: Adaptive Clipping for Private SGDcited by 77
  7. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  8. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  9. 2019Differential Privacy-enabled Federated Learning for Sensitive Health Datacited by 44
  10. 2018Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budgetcited by 31
  11. 2021Federated f-Differential Privacycited by 29
  12. 2018Three Tools for Practical Differential Privacycited by 20
  13. 2019An Adaptive and Fast Convergent Approach to Differentially Private Deep Learningcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 4; 2026: 3.

12 papers.

  1. 2024Activity Recognition on Avatar-Anonymized Datasets with Masked Differential Privacycited by 3
  2. 2023ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterationscited by 1
  3. 2023DP-DCAN: Differentially Private Deep Contrastive Autoencoder Network for Single-cell Clusteringcited by 1
  4. 2024BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocationcited by 1
  5. 2024Single-cell Curriculum Learning-based Deep Graph Embedding Clusteringcited by 0
  6. 2025Dyn-D2P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guaranteecited by 0
  7. 2025GCFL: A Gradient Correction-based Federated Learning Framework for Privacy-preserving CPSScited by 0
  8. 2025Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocationcited by 0
  9. 2025FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projectioncited by 0
  10. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0
  11. 2026An Adaptive Gradient Clipping and Noise Injection Mechanism for Differentially Private Federated Learningcited by 0
  12. 2026Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learningcited by 0