Federated Learning of User Authentication Models

TL;DR

This paper introduces FedUA, a federated learning framework for user authentication that preserves privacy by not sharing raw data or embeddings, enabling scalable and secure training of speaker verification models.

Contribution

FedUA is the first federated learning approach for user authentication that maintains privacy of raw inputs and embeddings, and supports scalable, dynamic user inclusion.

Findings

High true positive rates in speaker verification

Privacy-preserving training without sharing raw data or embeddings

Scalable with increasing number of users

Abstract

Machine learning-based User Authentication (UA) models have been widely deployed in smart devices. UA models are trained to map input data of different users to highly separable embedding vectors, which are then used to accept or reject new inputs at test time. Training UA models requires having direct access to the raw inputs and embedding vectors of users, both of which are privacy-sensitive information. In this paper, we propose Federated User Authentication (FedUA), a framework for privacy-preserving training of UA models. FedUA adopts federated learning framework to enable a group of users to jointly train a model without sharing the raw inputs. It also allows users to generate their embeddings as random binary vectors, so that, unlike the existing approach of constructing the spread out embeddings by the server, the embedding vectors are kept private as well. We show our method is privacy-preserving, scalable with number of users, and allows new users to be added to training without changing the output layer. Our experimental results on the VoxCeleb dataset for speaker verification shows our method reliably rejects data of unseen users at very high true positive rates.