Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification

[EN] The classification of motor imagery (MI) using Electroencephalography (EEG) plays a pivotal role in facilitating communication for individuals with physical limitations through Brain-Computer Interface (BCI) systems. Recent strides in Attention-Based Networks (ATN) have showcased remarkable per...

Descripción completa

Detalles Bibliográficos
Autores: Sayah Ben Aissa, Nour El Houda, Korichi, Ahmed, Lakas, Abderrahmane, Kerrache, Chaker Abdelaziz, Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/221674
Acceso en línea:https://riunet.upv.es/handle/10251/221674
Access Level:acceso abierto
Palabra clave:Brain-computer interfaces (BCI)
Electroencephalography (EEG)
Classification
Attention based networks
Adversarial attacks
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
id ES_f7e053096047ec72ecb79ef2f4ba5ef7
oai_identifier_str oai:riunet.upv.es:10251/221674
network_acronym_str ES
network_name_str España
repository_id_str
spelling Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classificationSayah Ben Aissa, Nour El HoudaKorichi, AhmedLakas, AbderrahmaneKerrache, Chaker AbdelazizTavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041Brain-computer interfaces (BCI)Electroencephalography (EEG)ClassificationAttention based networksAdversarial attacks09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación[EN] The classification of motor imagery (MI) using Electroencephalography (EEG) plays a pivotal role in facilitating communication for individuals with physical limitations through Brain-Computer Interface (BCI) systems. Recent strides in Attention-Based Networks (ATN) have showcased remarkable performance in EEG signal classification, presenting a promising alternative to conventional Convolutional Neural Networks (CNNs). However, while CNNs have been extensively analyzed for their resilience against adversarial attacks, the susceptibility of ATNs in comparable scenarios remains largely unexplored. This paper aims to fill this gap by investigating the robustness of ATNs in adversarial contexts. We propose a high-performing attention- based deep learning model specifically designed for classifying Motor Imagery (MI) brain signals extracted from EEG data. Subsequently, we conduct a thorough series of experiments to assess various attack strategies targeting ATNs employed in EEG-based BCI tasks. Our analysis utilizes the widely recognized BCI Competition 2a dataset to demonstrate the effectiveness of attention mechanisms in BCI endeavors. Despite achieving commendable classification results in terms of accuracy (87.15%) and kappa score (0.8287), our findings reveal the vulnerability of attention-based models to adversarial manipulations (accuracy: 9.07%, kappa score:-0.21), highlighting the imperative for bolstering the robustness of attention architectures for EEG classification tasks.This paper has been funded by Emirates Centre for Mobility Re-search at United Arab Emirates University, Grant #:31R269.Elsevier Inc.Departamento de Informática de Sistemas y ComputadoresEscuela Técnica Superior de Ingeniería InformáticaGrupo de Redes de ComputadoresUnited Arab Emirates UniversityAGENCIA ESTATAL DE INVESTIGACIONRepositorio Institucional de la Universitat Politècnica de València Riunet20242024-08-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://riunet.upv.es/handle/10251/221674reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-122580NB-I00 SISTEMAS INTELIGENTES DE SENSORIZACION PARA ECOSISTEMAS, ESPACIOS URBANOS Y MOVILIDAD SOSTENIBLEUnited Arab Emirates University https://doi.org/10.13039/501100006013 31R269open accesshttp://purl.org/coar/access_right/c_abf2Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:riunet.upv.es:10251/2216742026-06-13T07:49:27Z
dc.title.none.fl_str_mv Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
title Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
spellingShingle Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
Sayah Ben Aissa, Nour El Houda
Brain-computer interfaces (BCI)
Electroencephalography (EEG)
Classification
Attention based networks
Adversarial attacks
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
title_short Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
title_full Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
title_fullStr Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
title_full_unstemmed Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
title_sort Assessing robustness to adversarial attacks in attention-based networks: Case of EEG-based motor imagery classification
dc.creator.none.fl_str_mv Sayah Ben Aissa, Nour El Houda
Korichi, Ahmed
Lakas, Abderrahmane
Kerrache, Chaker Abdelaziz
Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
author Sayah Ben Aissa, Nour El Houda
author_facet Sayah Ben Aissa, Nour El Houda
Korichi, Ahmed
Lakas, Abderrahmane
Kerrache, Chaker Abdelaziz
Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
author_role author
author2 Korichi, Ahmed
Lakas, Abderrahmane
Kerrache, Chaker Abdelaziz
Tavares De Araujo Cesariny Calafate, Carlos Miguel|||0000-0001-5729-3041
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Informática de Sistemas y Computadores
Escuela Técnica Superior de Ingeniería Informática
Grupo de Redes de Computadores
United Arab Emirates University
AGENCIA ESTATAL DE INVESTIGACION
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Brain-computer interfaces (BCI)
Electroencephalography (EEG)
Classification
Attention based networks
Adversarial attacks
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
topic Brain-computer interfaces (BCI)
Electroencephalography (EEG)
Classification
Attention based networks
Adversarial attacks
09.- Desarrollar infraestructuras resilientes, promover la industrialización inclusiva y sostenible, y fomentar la innovación
description [EN] The classification of motor imagery (MI) using Electroencephalography (EEG) plays a pivotal role in facilitating communication for individuals with physical limitations through Brain-Computer Interface (BCI) systems. Recent strides in Attention-Based Networks (ATN) have showcased remarkable performance in EEG signal classification, presenting a promising alternative to conventional Convolutional Neural Networks (CNNs). However, while CNNs have been extensively analyzed for their resilience against adversarial attacks, the susceptibility of ATNs in comparable scenarios remains largely unexplored. This paper aims to fill this gap by investigating the robustness of ATNs in adversarial contexts. We propose a high-performing attention- based deep learning model specifically designed for classifying Motor Imagery (MI) brain signals extracted from EEG data. Subsequently, we conduct a thorough series of experiments to assess various attack strategies targeting ATNs employed in EEG-based BCI tasks. Our analysis utilizes the widely recognized BCI Competition 2a dataset to demonstrate the effectiveness of attention mechanisms in BCI endeavors. Despite achieving commendable classification results in terms of accuracy (87.15%) and kappa score (0.8287), our findings reveal the vulnerability of attention-based models to adversarial manipulations (accuracy: 9.07%, kappa score:-0.21), highlighting the imperative for bolstering the robustness of attention architectures for EEG classification tasks.
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-08-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/221674
url https://riunet.upv.es/handle/10251/221674
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-122580NB-I00 SISTEMAS INTELIGENTES DE SENSORIZACION PARA ECOSISTEMAS, ESPACIOS URBANOS Y MOVILIDAD SOSTENIBLE
United Arab Emirates University https://doi.org/10.13039/501100006013 31R269
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento - No comercial - Sin obra derivada (by-nc-nd)
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento - No comercial - Sin obra derivada (by-nc-nd)
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier Inc.
publisher.none.fl_str_mv Elsevier Inc.
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869424949621424128
score 15,81155

Similares en LA Referencia