# Free Privacy Protection for Wireless Federated Learning: Enjoy It or Suffer from It?

arXiv: https://arxiv.org/abs/2506.12749 · HTML: https://mlsanity.com/paper/2506.12749/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Local SGD Converges Fast and Communicates Little](https://mlsanity.com/paper/1805.09767/) (2018)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees](https://mlsanity.com/paper/2305.01588/) (2023)
- [Local Differential Privacy based Federated Learning for Internet of Things](https://mlsanity.com/paper/2004.08856/) (2020)
- [Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control](https://mlsanity.com/paper/2006.05459/) (2020)
- [On Analog Gradient Descent Learning over Multiple Access Fading Channels](https://mlsanity.com/paper/1908.07463/) (2019)
- [Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design](https://mlsanity.com/paper/2103.14272/) (2021)
- [Differentially Private Mixture of Generative Neural Networks](https://mlsanity.com/paper/1709.04514/) (2017)
- [Joint Privacy Enhancement and Quantization in Federated Learning](https://mlsanity.com/paper/2208.10888/) (2022)
- [Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networks](https://mlsanity.com/paper/2012.05137/) (2020)
- [Decentralized Wireless Federated Learning with Differential Privacy](https://mlsanity.com/paper/2109.09142/) (2021)
- [Amplitude-Varying Perturbation for Balancing Privacy and Utility in Federated Learning](https://mlsanity.com/paper/2303.04274/) (2023)
- [Imperfect CSI: A Key Factor of Uncertainty to Over-the-Air Federated Learning](https://mlsanity.com/paper/2307.12793/) (2023)
- [Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacy](https://mlsanity.com/paper/2304.07460/) (2023)
- [Decentralized Federated Learning Over Imperfect Communication Channels](https://mlsanity.com/paper/2405.12894/) (2024)
- [On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times](https://mlsanity.com/paper/2101.04163/) (2021)

## 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.