mlsanityData to 14 Oct 2026

AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning

arXiv 2105.00395 ↗First posted 2 May 2021cs.NI cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Wireless channels can be inherently privacy-preserving by distorting the received signals due to channel noise, and superpositioning multiple signals over-the-air. By harnessing these natural distortions and superpositions by wireless channels, we propose a novel privacy-preserving machine learning (ML) framework at the network edge, coined over-the-air mixup ML (AirMixML). In AirMixML, multiple workers transmit analog-modulated signals of their private data samples to an edge server who trains an ML model using the received noisy-and superpositioned samples. AirMixML coincides with model training using mixup data augmentation achieving comparable accuracy to that with raw data samples. From a privacy perspective, AirMixML is a differentially private (DP) mechanism limiting the disclosure of each worker's private sample information at the server, while the worker's transmit power determines the privacy disclosure level. To this end, we develop a fractional channel-inversion power control (PC) method, α-Dirichlet mixup PC (DirMix(α)-PC), wherein for a given global power scaling factor after channel inversion, each worker's local power contribution to the superpositioned signal is controlled by the Dirichlet dispersion ratio α. Mathematically, we derive a closed-form expression clarifying the relationship between the local and global PC factors to guarantee a target DP level. By simulations, we provide DirMix(α)-PC design guidelines to improve accuracy, privacy, and energy-efficiency. Finally, AirMixML with DirMix(α)-PC is shown to achieve reasonable accuracy compared to a privacy-violating baseline with neither superposition nor PC.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 11 of its 17 references that are in the map. First posted on arXiv 2 May 2021.

Builds on

11 of 17 references.

References · 11

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2017Renyi Differential Privacycited by 650
  5. 2018Federated Learning via Over-the-Air Computationcited by 219
  6. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  7. 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 73
  8. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 63
  9. 2021DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentationscited by 34
  10. 2020Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learningcited by 24
  11. 2020Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noisecited by 15

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3.

6 papers.

  1. 2022Differentially Private CutMix for Split Learning with Vision Transformercited by 13
  2. 2024Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystemcited by 3
  3. 2024Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMixcited by 2
  4. 2023SplitAMC: Split Learning for Robust Automatic Modulation Classificationcited by 1
  5. 2024PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Taskscited by 1
  6. 2023Semi-Federated Learning: Convergence Analysis and Optimization of A Hybrid Learning Frameworkcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Framework
  2. 2024Private Collaborative Edge Inference via Over-the-Air Computation
  3. 2022Over-the-Air Ensemble Inference with Model Privacy
  4. 2023Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
  5. 2026Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap
  6. 2022Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
  7. 2023Preserving Node-level Privacy in Graph Neural Networks
  8. 2023Privacy Side Channels in Machine Learning Systems