arrow
Return

Adversarial robustness benchmark for EEG-based brain-computer interfaces

delete2023-06-01
delete11
PRE
AI
L
Lubin Meng
X
Xue Jiang
D
Dongrui Wu *
DOI:10.1016/j.future.2023.01.028delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
Many machine learning approaches have been successfully applied to electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing approaches focused on making EEG-based BCIs more accurate, but few have considered their security. Recent studies have shown that EEG-based BCIs are vulnerable to adversarial attacks. To our knowledge, there is no study on adversarial defenses in EEG-based BCIs. This paper, for the first time, explores multiple classical and state-of-the-art adversarial defense approaches in EEG-based BCIs. Specifically, we demonstrated the performances of nine adversarial defense approaches on three convolutional neural networks and two EEG datasets, and established a comprehensive benchmark to evaluate their effectiveness in BCIs. Based on the evaluation results, we drew some key observations, hoping to inspire future adversarial defense research and attract more attention to the adversarial security of EEG-based BCIs. (c) 2023 Elsevier B.V. All rights reserved.
Keywords:
Brain-computer interface
Electroencephalogram
Adversarial example
Adversarial defense
Security

Journal

F
Future Generation Computer Systems-The International Journal of eScience
IF:
6.1
Papers:
6.9K
Citations:
2.3W

Organization

No organization information available
Cited Papers

Cited Papers

Gut ischemia/reperfusion-induced liver dysfunction occurs despite sustained oxygen consumption
err1992-05-01
err0
PREAI
errRenato S. Poggetti; Ernest E. Moore; Frederick A. Moore; Kaoru Koike; Anirban Banerjee
errShare
errSave
Universal adversarial perturbations for CNN classifiers in EEG-based BCIs
err2021-07-15
err28
errOAAI
errLiu, Zihan; Meng, Lubin; Zhang, Xiao; Fang, Weili; Wu, Dongrui
errShare
errSave
Breakdown of the Mott-Hubbard State inFe2O3: A First-Order Insulator-Metal Transition with Collapse of Magnetism at 50 GPa
err1999-06-07
err0
PREAI
errM. P. Pasternak; G. Kh. Rozenberg; G. Yu. Machavariani; O. Naaman; R. D. Taylor; R. Jeanloz
errShare
errSave
Tiny noise, big mistakes: adversarial perturbations induce errors in brain-computer interface spellers
err2020-09-10
err40
errOAAI
errZhang, Xiao; Wu, Dongrui; Ding, Lieyun; Luo, Hanbin; Lin, Chin-Teng; Jung, Tzyy-Ping; Chavarriaga, Ricardo
errShare
errSave
Deep learning models for electrocardiograms are susceptible to adversarial attack
err2020-03-09
err95
errOAAI
errHan, Xintian; Hu, Yuxuan; Foschini, Luca; Chinitz, Larry; Jankelson, Lior; Ranganath, Rajesh
errShare
errSave
errShare
errSave
Deep Learning With Convolutional Neural Networks for EEG Decoding and Visualization
err2017-08-07
err2.0K
errOAAI
errSchirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio
errShare
errSave
Clinical Studies of Iron Chelators in Malaria
err2009-02-17
err0
PREAI
errGeorge F. Mabeza; Godfrey Biemba; Victor R. Gordeuk
errShare
errSave
Multimodal BCIs: Target Detection, Multidimensional Control, and Awareness Evaluation in Patients With Disorder of Consciousness
err2016-02-01
err93
errOAAI
errLi, Yuanqing; Pan, Jiahui; Long, Jinyi; Yu, Tianyou; Wang, Fei; Yu, Zhuliang; Wu, Wei
errShare
errSave
researcher View more