mlsanityData to 7 Oct 2026

Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control

arXiv 2006.05459 ↗First posted 9 Jun 2020cs.IT cs.NI eess.SPcited by 62

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) refers to distributed protocols that avoid direct raw data exchange among the participating devices while training for a common learning task. This way, FL can potentially reduce the information on the local data sets that is leaked via communications. In order to provide formal privacy guarantees, however, it is generally necessary to put in place additional masking mechanisms. When FL is implemented in wireless systems via uncoded transmission, the channel noise can directly act as a privacy-inducing mechanism. This paper demonstrates that, as long as the privacy constraint level, measured via differential privacy (DP), is below a threshold that decreases with the signal-to-noise ratio (SNR), uncoded transmission achieves privacy "for free", i.e., without affecting the learning performance. More generally, this work studies adaptive power allocation (PA) for decentralized gradient descent in wireless FL with the aim of minimizing the learning optimality gap under privacy and power constraints. Both orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) transmission with "over-the-air-computing" are studied, and solutions are obtained in closed form for an offline optimization setting. Furthermore, heuristic online methods are proposed that leverage iterative one-step-ahead optimization. The importance of dynamic PA and the potential benefits of NOMA versus OMA are demonstrated through extensive simulations.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 13; 2023: 17; 2024: 10; 2025: 6; 2026: 2.

62 papers.

Sort:

By area:

  1. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  2. 2021Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applicationscited by 96
  3. 2021Federated Learning: A Signal Processing Perspectivecited by 49
  4. 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
  5. 2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 24
  6. 2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
  7. 2023Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directionscited by 21
  8. 2022A Survey on Over-the-Air Computationcited by 19
  9. 2023Machine Learning for Large-Scale Optimization in 6G Wireless Networkscited by 18
  10. 2023Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Surveycited by 17
  11. 2021Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysiscited by 13
  12. 2022Task-Oriented Over-the-Air Computation for Multi-Device Edge AIcited by 12
38 more
  1. 2021Hierarchical Over-the-Air Federated Edge Learningcited by 11
  2. 2022Over-the-Air Federated Learning via Second-Order Optimizationcited by 11
  3. 2022Over-the-Air Federated Edge Learning with Hierarchical Clusteringcited by 10
  4. 2023AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devicescited by 10
  5. 2023Over-the-Air Federated Learning and Optimizationcited by 10
  6. 2021Efficient and Reliable Overlay Networks for Decentralized Federated Learningcited by 9
  7. 2022Over-the-Air Ensemble Inference with Model Privacycited by 9
  8. 2023Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Predictioncited by 9
  9. 2021AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learningcited by 6
  10. 2021Wireless Federated Learning with Limited Communication and Differential Privacycited by 6
  11. 2021BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackerscited by 6
  12. 2021Robust Federated Learning via Over-The-Air Computationcited by 5
  13. 2022Differentially Private Federated Learning via Reconfigurable Intelligent Surfacecited by 5
  14. 2022Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networkscited by 5
  15. 2022Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbationscited by 5
  16. 2022Social-Aware Clustered Federated Learning with Customized Privacy Preservationcited by 5
  17. 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
  18. 2023Edge Intelligence Over the Air: Two Faces of Interference in Federated Learningcited by 5
  19. 2023Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channelscited by 5
  20. 2025Integrated Sensing, Communication, and Computation for Over-the-Air Federated Edge Learningcited by 5
  21. 2022Over-The-Air Federated Learning under Byzantine Attackscited by 4
  22. 2022CFLIT: Coexisting Federated Learning and Information Transfercited by 4
  23. 2023RHFedMTL: Resource-Aware Hierarchical Federated Multi-Task Learningcited by 4
  24. 2023Task-Oriented Integrated Sensing, Computation and Communication for Wireless Edge AIcited by 4
  25. 2024On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attackscited by 4
  26. 2024Private Collaborative Edge Inference via Over-the-Air Computationcited by 4
  27. 2021Over-the-Air Statistical Estimationcited by 3
  28. 2023Personalizing Federated Learning with Over-the-Air Computationscited by 3
  29. 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
  30. 2021Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learningcited by 2
  31. 2022Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMOcited by 2
  32. 2023Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clippingcited by 2
  33. 2024Rethinking Clustered Federated Learning in NOMA Enhanced Wireless Networkscited by 2
  34. 2024Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systemscited by 2
  35. 2023Accelerating Wireless Federated Learning via Nesterov's Momentum and Distributed Principle Component Analysiscited by 1
  36. 2023Over-the-Air Federated Averaging with Limited Power and Privacy Budgetscited by 1
  37. 2023Differentially Private Wireless Federated Learning Using Orthogonal Sequencescited by 1
  38. 2024Federated Low-Rank Adaptation with Differential Privacy over Wireless Networkscited by 1

50 most cited of 62 All 62 (JSON)