Federated Learning of User Authentication Models
- URL: http://arxiv.org/abs/2007.04618v1
- Date: Thu, 9 Jul 2020 08:04:38 GMT
- Title: Federated Learning of User Authentication Models
- Authors: Hossein Hosseini, Sungrack Yun, Hyunsin Park, Christos Louizos, Joseph
Soriaga and Max Welling
- Abstract summary: We propose Federated User Authentication (FedUA), a framework for privacy-preserving training of machine learning models.
FedUA adopts federated learning framework to enable a group of users to jointly train a model without sharing the raw inputs.
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.
- Score: 69.93965074814292
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- Personalized Language Model Learning on Text Data Without User Identifiers [79.36212347601223]
We propose to let each mobile device maintain a user-specific distribution to dynamically generate user embeddings.
To prevent the cloud from tracking users via uploaded embeddings, the local distributions of different users should either be derived from a linearly dependent space.
Evaluation on both public and industrial datasets reveals a remarkable improvement in accuracy from incorporating anonymous user embeddings.
arXiv Detail & Related papers (2025-01-10T15:46:19Z) - Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach [49.63614966954833]
Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy.
Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector.
This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously.
arXiv Detail & Related papers (2024-08-16T05:49:14Z) - Federated Face Forgery Detection Learning with Personalized Representation [63.90408023506508]
Deep generator technology can produce high-quality fake videos that are indistinguishable, posing a serious social threat.
Traditional forgery detection methods directly centralized training on data.
The paper proposes a novel federated face forgery detection learning with personalized representation.
arXiv Detail & Related papers (2024-06-17T02:20:30Z) - Partial Federated Learning [26.357723187375665]
Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices.
We propose a new algorithm called Partial Federated Learning (PartialFL), where a machine learning model is trained using data where a subset of data modalities can be made available to the server.
arXiv Detail & Related papers (2024-03-03T21:04:36Z) - Recovering from Privacy-Preserving Masking with Large Language Models [14.828717714653779]
We use large language models (LLMs) to suggest substitutes of masked tokens.
We show that models trained on the obfuscation corpora are able to achieve comparable performance with the ones trained on the original data.
arXiv Detail & Related papers (2023-09-12T16:39:41Z) - FedNST: Federated Noisy Student Training for Automatic Speech
Recognition [8.277567852741242]
Federated Learning (FL) enables training state-of-the-art Automatic Speech Recognition (ASR) models on user devices (clients) in distributed systems.
Key challenge facing practical adoption of FL for ASR is obtaining ground-truth labels on the clients.
A promising alternative is using semi-/self-supervised learning approaches to leverage unlabelled user data.
arXiv Detail & Related papers (2022-06-06T16:18:45Z) - Federated Learning of User Verification Models Without Sharing
Embeddings [73.27015469166166]
Federated User Verification (FedUV) is a framework in which users jointly learn a set of vectors and maximize the correlation of their instance embeddings with a secret linear combination of those vectors.
We show that choosing the linear combinations from the codewords of an error-correcting code allows users to collaboratively train the model without revealing their embedding vectors.
arXiv Detail & Related papers (2021-04-18T08:51:39Z) - Federated Learning-based Active Authentication on Mobile Devices [98.23904302910022]
User active authentication on mobile devices aims to learn a model that can correctly recognize the enrolled user based on device sensor information.
We propose a novel user active authentication training, termed as Federated Active Authentication (FAA)
We show that existing FL/SL methods are suboptimal for FAA as they rely on the data to be distributed homogeneously.
arXiv Detail & Related papers (2021-04-14T22:59:08Z) - Author2Vec: A Framework for Generating User Embedding [5.805785001237604]
We propose a novel end-to-end neural network-based user embedding system, Author2Vec.
The model incorporates sentence representations generated by BERT with a novel unsupervised pre-training objective, authorship classification.
Author2Vec successfully encoded useful user attributes and the generated user embedding performs well in downstream classification tasks.
arXiv Detail & Related papers (2020-03-17T23:31:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.