mlsanityData to 13 Oct 2026

Over-the-Air Ensemble Inference with Model Privacy

arXiv 2202.03129 ↗First posted 7 Feb 2022cs.LG cs.CR eess.SPcited by 10

Not on the map. Why?

Abstract (arXiv)

We consider distributed inference at the wireless edge, where multiple clients with an ensemble of models, each trained independently on a local dataset, are queried in parallel to make an accurate decision on a new sample. In addition to maximizing inference accuracy, we also want to maximize the privacy of local models. We exploit the superposition property of the air to implement bandwidth-efficient ensemble inference methods. We introduce different over-the-air ensemble methods and show that these schemes perform significantly better than their orthogonal counterparts, while using less resources and providing privacy guarantees. We also provide experimental results verifying the benefits of the proposed over-the-air inference approach, whose source code is shared publicly on Github.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

22 of 37 references.

References · 22

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
  2. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,281
  3. 2016Deep Learning with Differential Privacycited by 2,718
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,273
  5. 2019Searching for MobileNetV3cited by 1,990
  6. 2016Stealing Machine Learning Models via Prediction APIscited by 617
  7. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 456
  8. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 240
  9. 2018Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoisingcited by 218
  10. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 190
  11. 2019Federated Learning over Wireless Fading Channelscited by 182
  12. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 128
10 more
  1. 2021Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approachcited by 108
  2. 2020Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Controlcited by 63
  3. 2020Wireless Image Retrieval at the Edgecited by 58
  4. 2020Wireless Federated Learning with Local Differential Privacycited by 52
  5. 2020Communicate to Learn at the Edgecited by 28
  6. 2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
  7. 2020Private Wireless Federated Learning with Anonymous Over-the-Air Computationcited by 16
  8. 2019Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Aircited by 10
  9. 2020Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraintscited by 5
  10. 2021Progressive Feature Transmission for Split Inference at the Wireless Edgecited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 5; 2025: 2; 2026: 1.

10 papers.

  1. 2022Task-Oriented Over-the-Air Computation for Multi-Device Edge AIcited by 13
  2. 2024A Survey on Integrated Sensing, Communication, and Computationcited by 12
  3. 2024Collaborative Edge AI Inference over Cloud-RANcited by 5
  4. 2024Private Collaborative Edge Inference via Over-the-Air Computationcited by 5
  5. 2023Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networkscited by 2
  6. 2024Collaborative Inference over Wireless Channels with Feature Differential Privacycited by 1
  7. 2024Federated Learning for Collaborative Inference Systems: The Case of Early Exit Networkscited by 0
  8. 2025Multi-Rate Task-Oriented Communication for Multi-Edge Cooperative Inferencecited by 0
  9. 2025Adversary-Aware Private Inference over Wireless Channelscited by 0
  10. 2026SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmissioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective
  2. 2021AirMixML: Over-the-Air Data Mixup for Inherently Privacy-Preserving Edge Machine Learning
  3. 2023Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
  4. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture
  5. 2024Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Framework
  6. 2022Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
  7. 2026Logit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks
  8. 2025Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing