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

TL;DR

This paper introduces a privacy-enhanced wireless federated learning method that leverages over-the-air computation and device anonymization to improve efficiency and reduce noise injection compared to traditional differential privacy approaches.

Contribution

It proposes a novel approach combining over-the-air computation with device anonymization to boost privacy and efficiency in wireless federated learning.

Findings

Enhanced privacy through device anonymization and over-the-air computation

Reduced noise injection improves learning performance

More efficient spectrum utilization in wireless FL

Abstract

In conventional federated learning (FL), differential privacy (DP) guarantees can be obtained by injecting additional noise to local model updates before transmitting to the parameter server (PS). In the wireless FL scenario, we show that the privacy of the system can be boosted by exploiting over-the-air computation (OAC) and anonymizing the transmitting devices. In OAC, devices transmit their model updates simultaneously and in an uncoded fashion, resulting in a much more efficient use of the available spectrum. We further exploit OAC to provide anonymity for the transmitting devices. The proposed approach improves the performance of private wireless FL by reducing the amount of noise that must be injected.