Differentially Private Wireless Federated Learning Using Orthogonal Sequences
This work addresses privacy concerns in wireless federated learning systems, offering a flexible tradeoff between model convergence and privacy levels, but it is incremental as it builds on existing AirComp and differential privacy techniques.
The paper tackles the problem of preserving privacy in wireless federated learning by proposing FLORAS, a method that uses orthogonal sequences to eliminate the need for channel state information and provides differential privacy guarantees, with experimental results showing advantages over baseline methods.
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.