Free Privacy Protection for Wireless Federated Learning: Enjoy It or Suffer from It?
Not on the map. Why?
Abstract (arXiv)
Inherent communication noises have the potential to preserve privacy for wireless federated learning (WFL) but have been overlooked in digital communication systems predominantly using floating-point number standards, e.g., IEEE 754, for data storage and transmission. This is due to the potentially catastrophic consequences of bit errors in floating-point numbers, e.g., on the sign or exponent bits. This paper presents a novel channel-native bit-flipping differential privacy (DP) mechanism tailored for WFL, where transmit bits are randomly flipped and communication noises are leveraged, to collectively preserve the privacy of WFL in digital communication systems. The key idea is to interpret the bit perturbation at the transmitter and bit errors caused by communication noises as a bit-flipping DP process. This is achieved by designing a new floating-point-to-fixed-point conversion method that only transmits the bits in the fraction part of model parameters, hence eliminating the need for transmitting the sign and exponent bits and preventing the catastrophic consequence of bit errors. We analyze a new metric to measure the bit-level distance of the model parameters and prove that the proposed mechanism satisfies (λ,ε)-R'enyi DP and does not violate the WFL convergence. Experiments validate privacy and convergence analysis of the proposed mechanism and demonstrate its superiority to the state-of-the-art Gaussian mechanisms that are channel-agnostic and add Gaussian noise for privacy protection.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 15 Jun 2025.
Builds on
24 of 45 references.
References · 24
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2017Renyi Differential Privacycited by 643
- 2018Local SGD Converges Fast and Communicates Littlecited by 595
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 199
- 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
- 2020The Discrete Gaussian for Differential Privacycited by 134
- 2023Revisiting Gradient Clipping: Stochastic bias and tight convergence guaranteescited by 83
- 2020Local Differential Privacy based Federated Learning for Internet of Thingscited by 74
12 more
- 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 62
- 2019On Analog Gradient Descent Learning over Multiple Access Fading Channelscited by 61
- 2021Hierarchical Federated Learning with Quantization: Convergence Analysis and System Designcited by 47
- 2017Differentially Private Mixture of Generative Neural Networkscited by 39
- 2022Joint Privacy Enhancement and Quantization in Federated Learningcited by 34
- 2020Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networkscited by 29
- 2021Decentralized Wireless Federated Learning with Differential Privacycited by 18
- 2023Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learningcited by 13
- 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
- 2023Imperfect CSI: A Key Factor of Uncertainty to Over-the-Air Federated Learningcited by 5
- 2024Decentralized Federated Learning Over Imperfect Communication Channelscited by 5
- 2021On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Timescited by 2
Built on by
Not cited yet.