A Federated Learning Approach for Continuous User Identification

R. Veiga; R. Flexa; L. Bastos; I. Medeiros; D. Rosario; E. Cerqueira; S. Zeadally; L. Villas

doi:10.1109/WF-IoT58464.2023.10539581

A Federated Learning Approach for Continuous User Identification

R. Veiga, R. Flexa, L. Bastos, I. Medeiros, D. Rosario, E. Cerqueira, S. Zeadally, L. Villas

School of Information Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Smartphones will remain key devices in the 6G era, where many applications and services will collect and share a lot of sensitive data. Smartphones can collect biometric behaviors from users during the use of devices, and the data will be analyzed and processed by machine learning approaches, where privacy and security issues are mandatory in 6G systems. However, an identification system using a mobile device does not need to share sensitive data, focusing on data security and sharing just user weights. In this paper, we propose a Federated Learning (FL) approach based on accelerometer and gyroscope data to identify a user's behavior for continuous user identification. This study evaluates the performance of accuracy, Loss, False Rejection Rate (FRR), weights and runtime processing of different Convolutional Neural Networks (CNN) for continuous user identification. The simulation results show that the best configuration is when using FCN with 4 and 3 epochs.

Original language	English
Title of host publication	2023 IEEE World Forum on Internet of Things
Subtitle of host publication	The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023
ISBN (Electronic)	9798350311617
DOIs	https://doi.org/10.1109/WF-IoT58464.2023.10539581
State	Published - 2023
Event	9th IEEE World Forum on Internet of Things, WF-IoT 2023 - Hybrid, Aveiro, Portugal Duration: Oct 12 2023 → Oct 27 2023

Publication series

Name	2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023

Conference

Conference	9th IEEE World Forum on Internet of Things, WF-IoT 2023
Country/Territory	Portugal
City	Hybrid, Aveiro
Period	10/12/23 → 10/27/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Federated Learning
Identification
Internet of things

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Hardware and Architecture
Safety, Risk, Reliability and Quality
Modeling and Simulation
Instrumentation

Access to Document

10.1109/WF-IoT58464.2023.10539581

Cite this

Veiga, R., Flexa, R., Bastos, L., Medeiros, I., Rosario, D., Cerqueira, E., Zeadally, S., & Villas, L. (2023). A Federated Learning Approach for Continuous User Identification. In 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023 (2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023). https://doi.org/10.1109/WF-IoT58464.2023.10539581

@inproceedings{a415ab55b24b40d59fabe8de290f7b7f,

title = "A Federated Learning Approach for Continuous User Identification",

abstract = "Smartphones will remain key devices in the 6G era, where many applications and services will collect and share a lot of sensitive data. Smartphones can collect biometric behaviors from users during the use of devices, and the data will be analyzed and processed by machine learning approaches, where privacy and security issues are mandatory in 6G systems. However, an identification system using a mobile device does not need to share sensitive data, focusing on data security and sharing just user weights. In this paper, we propose a Federated Learning (FL) approach based on accelerometer and gyroscope data to identify a user's behavior for continuous user identification. This study evaluates the performance of accuracy, Loss, False Rejection Rate (FRR), weights and runtime processing of different Convolutional Neural Networks (CNN) for continuous user identification. The simulation results show that the best configuration is when using FCN with 4 and 3 epochs.",

keywords = "Federated Learning, Identification, Internet of things",

author = "R. Veiga and R. Flexa and L. Bastos and I. Medeiros and D. Rosario and E. Cerqueira and S. Zeadally and L. Villas",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 9th IEEE World Forum on Internet of Things, WF-IoT 2023 ; Conference date: 12-10-2023 Through 27-10-2023",

year = "2023",

doi = "10.1109/WF-IoT58464.2023.10539581",

language = "English",

series = "2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023",

booktitle = "2023 IEEE World Forum on Internet of Things",

}

Veiga, R, Flexa, R, Bastos, L, Medeiros, I, Rosario, D, Cerqueira, E, Zeadally, S & Villas, L 2023, A Federated Learning Approach for Continuous User Identification. in 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023. 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023, 9th IEEE World Forum on Internet of Things, WF-IoT 2023, Hybrid, Aveiro, Portugal, 10/12/23. https://doi.org/10.1109/WF-IoT58464.2023.10539581

A Federated Learning Approach for Continuous User Identification. / Veiga, R.; Flexa, R.; Bastos, L. et al.
2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023. 2023. (2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Federated Learning Approach for Continuous User Identification

AU - Veiga, R.

AU - Flexa, R.

AU - Bastos, L.

AU - Medeiros, I.

AU - Rosario, D.

AU - Cerqueira, E.

AU - Zeadally, S.

AU - Villas, L.

PY - 2023

Y1 - 2023

N2 - Smartphones will remain key devices in the 6G era, where many applications and services will collect and share a lot of sensitive data. Smartphones can collect biometric behaviors from users during the use of devices, and the data will be analyzed and processed by machine learning approaches, where privacy and security issues are mandatory in 6G systems. However, an identification system using a mobile device does not need to share sensitive data, focusing on data security and sharing just user weights. In this paper, we propose a Federated Learning (FL) approach based on accelerometer and gyroscope data to identify a user's behavior for continuous user identification. This study evaluates the performance of accuracy, Loss, False Rejection Rate (FRR), weights and runtime processing of different Convolutional Neural Networks (CNN) for continuous user identification. The simulation results show that the best configuration is when using FCN with 4 and 3 epochs.

AB - Smartphones will remain key devices in the 6G era, where many applications and services will collect and share a lot of sensitive data. Smartphones can collect biometric behaviors from users during the use of devices, and the data will be analyzed and processed by machine learning approaches, where privacy and security issues are mandatory in 6G systems. However, an identification system using a mobile device does not need to share sensitive data, focusing on data security and sharing just user weights. In this paper, we propose a Federated Learning (FL) approach based on accelerometer and gyroscope data to identify a user's behavior for continuous user identification. This study evaluates the performance of accuracy, Loss, False Rejection Rate (FRR), weights and runtime processing of different Convolutional Neural Networks (CNN) for continuous user identification. The simulation results show that the best configuration is when using FCN with 4 and 3 epochs.

KW - Federated Learning

KW - Identification

KW - Internet of things

UR - http://www.scopus.com/inward/record.url?scp=85195416589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85195416589&partnerID=8YFLogxK

U2 - 10.1109/WF-IoT58464.2023.10539581

DO - 10.1109/WF-IoT58464.2023.10539581

M3 - Conference contribution

AN - SCOPUS:85195416589

T3 - 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023

BT - 2023 IEEE World Forum on Internet of Things

T2 - 9th IEEE World Forum on Internet of Things, WF-IoT 2023

Y2 - 12 October 2023 through 27 October 2023

ER -

Veiga R, Flexa R, Bastos L, Medeiros I, Rosario D, Cerqueira E et al. A Federated Learning Approach for Continuous User Identification. In 2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023. 2023. (2023 IEEE World Forum on Internet of Things: The Blue Planet: A Marriage of Sea and Space, WF-IoT 2023). doi: 10.1109/WF-IoT58464.2023.10539581

A Federated Learning Approach for Continuous User Identification

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this