EEG-based brain-computer interfaces are vulnerable to backdoor attacks

Meng, Lubin; Jiang, Xue; Huang, Jian; Zeng, Zhigang; Yu, Shan; Jung, Tzyy-Ping; Lin, Chin-Teng; Chavarriaga, Ricardo; Wu, Dongrui

doi:10.1109/TNSRE.2023.3273214

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-27853

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	EEG-based brain-computer interfaces are vulnerable to backdoor attacks
Authors:	Meng, Lubin Jiang, Xue Huang, Jian Zeng, Zhigang Yu, Shan Jung, Tzyy-Ping Lin, Chin-Teng Chavarriaga, Ricardo Wu, Dongrui
et. al:	No
DOI:	10.1109/TNSRE.2023.3273214 10.21256/zhaw-27853
Published in:	IEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume(Issue):	31
Page(s):	2224
Pages to:	2234
Issue Date:	2023
Publisher / Ed. Institution:	IEEE
ISSN:	1534-4320 1558-0210
Language:	English
Subjects:	Electroencephalography; Brain modeling; Security; Brain-computer interface; Machine learning; Adversarial attack; Backdoor attack
Subject (DDC):	006: Special computer methods
Abstract:	Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This paper proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which makes adversarial attacks much easier to implement. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it.
URI:	https://digitalcollection.zhaw.ch/handle/11475/27853
Fulltext version:	Published version
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
Departement:	School of Engineering
Organisational Unit:	Centre for Artificial Intelligence (CAI)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2023_Meng-etal_EEG-based_brain-computer-interfaces-vulnerable-backdoor-attacks_EMB.pdf		3.87 MB	Adobe PDF	View/Open

Show full item record

Meng, L., Jiang, X., Huang, J., Zeng, Z., Yu, S., Jung, T.-P., Lin, C.-T., Chavarriaga, R., & Wu, D. (2023). EEG-based brain-computer interfaces are vulnerable to backdoor attacks. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 2224–2234. https://doi.org/10.1109/TNSRE.2023.3273214

Meng, L. et al. (2023) ‘EEG-based brain-computer interfaces are vulnerable to backdoor attacks’, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, pp. 2224–2234. Available at: https://doi.org/10.1109/TNSRE.2023.3273214.

L. Meng et al., “EEG-based brain-computer interfaces are vulnerable to backdoor attacks,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 2224–2234, 2023, doi: 10.1109/TNSRE.2023.3273214.

MENG, Lubin, Xue JIANG, Jian HUANG, Zhigang ZENG, Shan YU, Tzyy-Ping JUNG, Chin-Teng LIN, Ricardo CHAVARRIAGA und Dongrui WU, 2023. EEG-based brain-computer interfaces are vulnerable to backdoor attacks. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2023. Bd. 31, S. 2224–2234. DOI 10.1109/TNSRE.2023.3273214

Meng, Lubin, Xue Jiang, Jian Huang, Zhigang Zeng, Shan Yu, Tzyy-Ping Jung, Chin-Teng Lin, Ricardo Chavarriaga, and Dongrui Wu. 2023. “EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks.” IEEE Transactions on Neural Systems and Rehabilitation Engineering 31: 2224–34. https://doi.org/10.1109/TNSRE.2023.3273214.

Meng, Lubin, et al. “EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks.” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, 2023, pp. 2224–34, https://doi.org/10.1109/TNSRE.2023.3273214.