mlsanityData to 7 Oct 2026

Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels

arXiv 2306.10982 ↗First posted 19 Jun 2023cs.IT cs.CR cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables edge devices to collaboratively train machine learning models, with model communication replacing direct data uploading. While over-the-air model aggregation improves communication efficiency, uploading models to an edge server over wireless networks can pose privacy risks. Differential privacy (DP) is a widely used quantitative technique to measure statistical data privacy in FL. Previous research has focused on over-the-air FL with a single-antenna server, leveraging communication noise to enhance user-level DP. This approach achieves the so-called "free DP" by controlling transmit power rather than introducing additional DP-preserving mechanisms at devices, such as adding artificial noise. In this paper, we study differentially private over-the-air FL over a multiple-input multiple-output (MIMO) fading channel. We show that FL model communication with a multiple-antenna server amplifies privacy leakage as the multiple-antenna server employs separate receive combining for model aggregation and information inference. Consequently, relying solely on communication noise, as done in the multiple-input single-output system, cannot meet high privacy requirements, and a device-side privacy-preserving mechanism is necessary for optimal DP design. We analyze the learning convergence and privacy loss of the studied FL system and propose a transceiver design algorithm based on alternating optimization. Numerical results demonstrate that the proposed method achieves a better privacy-learning trade-off compared to prior work.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 24 of its 46 references that are in the map. First posted on arXiv 19 Jun 2023.

Builds on

24 of 46 references.

References · 24

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  5. 2018Local SGD Converges Fast and Communicates Littlecited by 595
  6. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  7. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  8. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  9. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  10. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  11. 2018Federated Learning via Over-the-Air Computationcited by 215
  12. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
12 more
  1. 2019The Roadmap to 6G -- AI Empowered Wireless Networkscited by 150
  2. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 62
  3. 2020Wireless Federated Learning with Local Differential Privacycited by 50
  4. 2020Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approachcited by 32
  5. 2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
  6. 2020Private Wireless Federated Learning with Anonymous Over-the-Air Computationcited by 16
  7. 2020Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noisecited by 14
  8. 2020Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraintscited by 5
  9. 2022Differentially Private Federated Learning via Reconfigurable Intelligent Surfacecited by 5
  10. 2022CFLIT: Coexisting Federated Learning and Information Transfercited by 4
  11. 2021Privacy-Preserving Wireless Federated Learning Exploiting Inherent Hardware Impairmentscited by 2
  12. 2021Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 4.

5 papers.

  1. 2025A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networkscited by 3
  2. 2025Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Schedulingcited by 1
  3. 2025Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Stationcited by 1
  4. 2024Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Frameworkcited by 0
  5. 2025Convergence-Privacy-Fairness Trade-Off in Personalized Federated Learningcited by 0