Differentially Private Wireless Federated Learning Using Orthogonal Sequences
Not on the map. Why?
Abstract (arXiv)
We propose a privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for single-input single-output (SISO) wireless federated learning (FL) systems. From the perspective of communication designs, FLORAS eliminates the requirement of channel state information at the transmitters (CSIT) by leveraging the properties of orthogonal sequences. From the privacy perspective, we prove that FLORAS offers both item-level and client-level differential privacy (DP) guarantees. Moreover, by properly adjusting the system parameters, FLORAS can flexibly achieve different DP levels at no additional cost. A new FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between the achieved convergence rate and differential privacy levels. Experimental results demonstrate the advantages of FLORAS compared with the baseline AirComp method, and validate that the analytical results can guide the design of privacy-preserving FL with different tradeoff requirements on the model convergence and privacy levels.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 46 of its 76 references that are in the map. First posted on arXiv 14 Jun 2023.
Builds on
46 of 76 references.
References · 46
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 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
- 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 339
- 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
- 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
- 2019Differentially Private Learning with Adaptive Clippingcited by 218
- 2018Federated Learning via Over-the-Air Computationcited by 215
34 more
- 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 199
- 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
- 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
- 2019Federated Learning over Wireless Fading Channelscited by 178
- 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 157
- 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 140
- 2019Federated Learning for Wireless Communications: Motivation, Opportunities and Challengescited by 128
- 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
- 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
- 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
- 2021Learning with User-Level Privacycited by 72
- 2015Perturbed Iterate Analysis for Asynchronous Stochastic Optimizationcited by 67
- 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 66
- 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
- 2019On Safeguarding Privacy and Security in the Framework of Federated Learningcited by 55
- 2020Wireless Federated Learning with Local Differential Privacycited by 50
- 2020Design and Analysis of Uplink and Downlink Communications for Federated Learningcited by 48
- 2020Blind Federated Edge Learningcited by 42
- 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 38
- 2021Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraintscited by 34
- 2021Dynamic Differential-Privacy Preserving SGDcited by 29
- 2021Convergence Analysis and System Design for Federated Learning over Wireless Networkscited by 25
- 2021Low-Latency Federated Learning over Wireless Channels with Differential Privacycited by 24
- 2021Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregationcited by 22
- 2020Private Wireless Federated Learning with Anonymous Over-the-Air Computationcited by 16
- 2021Adaptive Transmission Scheduling in Wireless Networks for Asynchronous Federated Learningcited by 15
- 2022Random Orthogonalization for Federated Learning in Massive MIMO Systemscited by 13
- 2021Joint Client Scheduling and Resource Allocation under Channel Uncertainty in Federated Learningcited by 10
- 2022Over-the-Air Federated Learning with Energy Harvesting Devicescited by 8
- 2019Optimized Power Control for Over-the-Air Computation in Fading Channelscited by 7
- 2021User Scheduling for Federated Learning Through Over-the-Air Computationcited by 7
- 2022Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learningcited by 7
- 2022Generalizing DP-SGD with Shuffling and Batch Clippingcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.