Differentially Private Wireless Federated Learning Using Orthogonal Sequences

06/14/2023

∙

We propose a novel privacy-preserving uplink over-the-air computation (AirComp) method, termed FLORAS, for single-input single-output (SISO) wireless federated learning (FL) systems. From the communication design perspective, 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 can offer both item-level and client-level differential privacy (DP) guarantees. Moreover, by adjusting the system parameters, FLORAS can flexibly achieve different DP levels at no additional cost. A novel FL convergence bound is derived which, combined with the privacy guarantees, allows for a smooth tradeoff between convergence rate and differential privacy levels. Numerical results demonstrate the advantages of FLORAS compared with the baseline AirComp method, and validate that our analytical results can guide the design of privacy-preserving FL with different tradeoff requirements on the model convergence and privacy levels.

READ FULL TEXT

Differentially Private Wireless Federated Learning Using Orthogonal Sequences

Private Wireless Federated Learning with Anonymous Over-the-Air Computation

Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels

Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning

Federated Learning with Differential Privacy: Algorithms and Performance Analysis

Fed-GLOSS-DP: Federated, Global Learning using Synthetic Sets with Record Level Differential Privacy

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise

Differentially Private CutMix for Split Learning with Vision Transformer

Differentially Private Wireless Federated Learning Using Orthogonal Sequences

Related Research

Private Wireless Federated Learning with Anonymous Over-the-Air Computation

Differentially Private Over-the-Air Federated Learning Over MIMO Fading Channels

Kernel Normalized Convolutional Networks for Privacy-Preserving Machine Learning

Federated Learning with Differential Privacy: Algorithms and Performance Analysis

Fed-GLOSS-DP: Federated, Global Learning using Synthetic Sets with Record Level Differential Privacy

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise

Differentially Private CutMix for Split Learning with Vision Transformer