Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) is a distributed learning paradigm that preserves privacy by eliminating the need to exchange raw data during training. In its prototypical edge instantiation with underlying wireless transmissions enabled by analog over-the-air computing (AirComp), referred to as over-the-air FL (AirFL), the inherent channel noise plays a unique role of frenemy in the sense that it degrades training due to noisy global aggregation while providing a natural source of randomness for privacy-preserving mechanisms, formally quantified by differential privacy (DP). It remains, nevertheless, challenging to effectively harness such channel impairments, as prior arts, under assumptions of either simple channel models or restricted types of loss functions, mostly considering (local) DP enhancement with a single-round or non-convergent bound on privacy loss. In this paper, we study AirFL over multiple-access fading channels with a multi-antenna base station (BS) subject to user-level DP requirements. Despite a recent study, which claimed in similar settings that artificial noise (AN) must be injected to ensure DP in general, we demonstrate, on the contrary, that DP can be gained as a perk even without employing any AN. Specifically, we derive a novel bound on DP that converges under general bounded-domain assumptions on model parameters, along with a convergence bound with general smooth and non-convex loss functions. Next, we optimize over receive beamforming and power allocations to characterize the optimal convergence-privacy trade-offs, which also reveal explicit conditions in which DP is achievable without compromising training. Finally, our theoretical findings are validated by extensive numerical results.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 29 of its 57 references that are in the map. First posted on arXiv 27 Oct 2025.
Builds on
29 of 57 references.
References · 29
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
- 2016Deep Learning with Differential Privacycited by 2,718
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,273
- 2021Towards Personalized Federated Learningcited by 463
- 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 456
- 2018Federated Learning via Over-the-Air Computationcited by 219
- 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 202
- 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 190
- 2020Private Stochastic Convex Optimization: Optimal Rates in Linear Timecited by 153
- 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
- 2018Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcited by 128
17 more
- 2020One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysiscited by 112
- 2021Hyperparameter Tuning with Renyi Differential Privacycited by 104
- 2018Privacy Amplification by Iterationcited by 98
- 2020Improved Analysis of Clipping Algorithms for Non-convex Optimizationcited by 89
- 2022Automatic Clipping: Differentially Private Deep Learning Made Easier and Strongercited by 88
- 2018Private Selection from Private Candidatescited by 75
- 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 63
- 2022Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Losscited by 60
- 2021Optimized Power Control Design for Over-the-Air Federated Edge Learningcited by 48
- 2020Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noisecited by 15
- 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 14
- 2023Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channelscited by 5
- 2023Task-Oriented Integrated Sensing, Computation and Communication for Wireless Edge AIcited by 4
- 2023AirFL-Mem: Improving Communication-Learning Trade-Off by Long-Term Memorycited by 4
- 2025An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Lossescited by 4
- 2024Pre-Training and Personalized Fine-Tuning via Over-the-Air Federated Meta-Learning: Convergence-Generalization Trade-Offscited by 3
- 2023Convergence Analysis of Over-the-Air FL with Compression and Power Control via Clippingcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.