Intelligent and inclusive EEG-driven authentication for gender fairness and cognitive impairment

Abstract

User authentication plays a key role in user modelling within computing systems, particularly for both normal control (NC) and Alzheimer’s disease (AD) users. Conventional authentication methods are vulnerable to external attacks and often rely on memory, which poses challenges for AD users experiencing cognitive decline. Electroencephalography (EEG) signals offer an alternative due to their subject-specific and difficult-to-replicate properties. However, differences in EEG patterns between NC and AD populations require intelligent authentication approaches that can generalise across heterogeneous user groups. This study proposes Biometric using microstates of EEG (Bio-MEEG), an intelligent EEG authentication framework that integrates EEG microstate analysis, one-dimensional convolutional neural networks (1D-CNNs), and ensemble learning based on echo state networks (ESNs) for user authentication under a closed-set, repeated-sample identification setting. The model is evaluated on 1,015 samples from 203 participants across multiple countries and EEG configurations. Results show that Bio-MEEG achieves stable authentication performance with minimal accuracy fluctuation across demographic subgroups and remains robust under feature-space adversarial perturbations. By supporting both NC and AD users without significant performance disparity, the proposed framework contributes toward more accessible, intelligent, and reliable EEG-based authentication systems.

Keywords

EEG-based authentication / EEG microstates / ensemble learning / algorithmic fairness / Alzheimer’s disease / adversarial robustness / brain-computer interface

References

[1] Lassak L,Golla M,Dürmuth M.A comparative long-term study of fallback authentication schemes. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery: 2024; pp. 1-19.

[2] Constantinides A,Fidas C.Security and usability of a personalized user authentication paradigm: insights from a longitudinal study with three healthcare organizations.ACM Trans Comput Healthc2023;4:1-40

[3] He H,Li Y.MSAFNet: a novel approach to facial expression recognition in embodied AI systems.Intell Robot2025;5:313-32

[4] Nakamura T,Mandic DP.In-ear EEG biometrics for feasible and readily collectable real-world person authentication.IEEE Trans Inf Forensics Secur2018;13:648-61

[5] Aldayel M,Al-Nafjan A.Systematic review of brain-computer interface based user authentication system: trends, challenges, and directions.IEEE Access2024;12:96848-61

[6] Seyfizadeh A,Tovote P,Volkmann J.Enhancing security in brain–computer interface applications with deep learning: electroencephalogram-based user identification.Expert Syst Appl2024;253:124218

[7] Colafiglio T,Sorino P.EmoSynth real time emotion-driven sound texture synthesis via brain-computer interface. In Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization (UMAP). Association for Computing Machinery: 2024; pp. 616-21.

[8] Białas K,Chałupnik R.Multifactor authentication system using simplified EEG brain–computer interface.IEEE Trans Hum Mach Syst2022;52:867-76

[9] Peng Y,Zuo Z,Wang Z.A rehabilitation design concept based on brain–computer interface and McKibben artificial muscle.Healthc Rehabil2026;2:100066

[10] Bidgoly AJ,Arezoumand Z.A survey on methods and challenges in EEG based authentication.Comput Secur2020;93:101788

[11] Jin J,Cai H.Affective EEG-based person identification with continual learning.IEEE Trans Instrum Meas2024;73:1-16

[12] Chaurasia AK,Strufe T,Cabarcos PA.NeuroIDBench: an open-source benchmark framework for the standardization of methodology in brainwave-based authentication research.J Inf Secur Appl2024;85:103832

[13] Nguyen QT,Williams-King D,Duong-Trung N.Explainable AI for dementia detection using EEG microstates. In Companion Proceedings of the 31st International Conference on Intelligent User Interfaces. Association for Computing Machinery: 2026; pp. 39-42.

[14] Adebisi AT,Veluvolu KC.EEG-based brain functional network analysis for differential identification of dementia-related disorders and their onset.IEEE Trans Neural Syst Rehabil Eng2024;32:1198-209

[15] Hogges J,Sneha S.A two-step password authentication system for Alzheimer patients. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), Madrid, Spain, July 13-17, 2020. IEEE: 2020; pp. 1444-8.

[16] Raivio MM,Laakkonen ML,Pitkälä KH.The use of legal guardians and financial powers of attorney among home-dwellers with Alzheimer’s disease living with their spousal caregivers.J Med Ethics2008;34:882-6

[17] Gaikwad S,Haque MA.Senescence, brain inflammation, and oligomeric tau drive cognitive decline in Alzheimer’s disease: evidence from clinical and preclinical studies.Alzheimers Dement2024;20:709-27 PMCID:PMC10841264

[18] Hughes J,Hutchings A.The art of cybercrime community research.ACM Comput Surv2024;56:1-26

[19] Lassi M,Mazzeo S.Degradation of EEG microstates patterns in subjective cognitive decline and mild cognitive impairment: early biomarkers along the Alzheimer’s disease continuum?.NeuroImage Clin2023;38:103407 PMCID:PMC10149415

[20] Huber M,Boutros F,Damer N.Bias and diversity in synthetic-based face recognition. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 2024; pp. 6215-26.

[21] Drozdowski P,Dantcheva A,Busch C.Demographic bias in biometrics: a survey on an emerging challenge.IEEE Trans Technol Soc2020;1:89-103

[22] Pappula M.An ADHD diagnostic interface based on EEG spectrograms and deep learning techniques. In 2024 20th International Symposium on Medical Information Processing and Analysis (SIPAIM), Antigua, Guatemala, Nov 13-15, 2024. IEEE: 2024; p. 1-4.

[23] Haider CMR,Zhou Y.Unfair AI: it isn’t just biased data. In 2022 IEEE International Conference on Data Mining (ICDM), Orlando, USA, Nov 28 - Dec 01, 2022. IEEE: 2022; pp. 957-62.

[24] Sun J,Shen A,Gao X.An ensemble learning model for continuous cognition assessment based on resting-state EEG.NPJ Aging2024;10:1 PMCID:PMC10762083

[25] Sun C,Cai D,Hong S.A systematic review of echo state networks from design to application.IEEE Trans Artif Intell2024;5:23-37

[26] Wang Z.TransTab: learning transferable tabular transformers across tables.Adv Neural Inf Process Syst2022;35:2902-15

[27] Shwartz-Ziv R.Tabular data: deep learning is not all you need.Inf Fusion2022;81:84-90

[28] Goetz L,Vandersluis R.Generalization - a key challenge for responsible AI in patient-facing clinical applications.NPJ Digit Med2024;7:126 PMCID:PMC11109198

[29] Chen Y,Schlattner I.A high-security EEG-based login system with RSVP stimuli and dry electrodes.IEEE Trans Inf Forensics Secur2016;11:2635-47

[30] Wu Q,Zeng Y,Tong L.Anti-deception: reliable EEG-based biometrics with real-time capability from the neural response of face rapid serial visual presentation.BioMed Eng OnLine2018;17:55

[31] Mu Z,Min J.EEG-based person authentication using a fuzzy entropy-related approach with two electrodes.Entropy2016;18:432

[32] Wu Q,Zhang C,Yan B.An EEG-based person authentication system with open-set capability combining eye blinking signals.Sensors2018;18:335 PMCID:PMC5855894

[33] Thomas KP.EEG-based biometric authentication using gamma band power during rest state.Circuits Syst Signal Process2018;37:277-89

[34] Kumar P,Kaur B,Scheme E.Fusion of neuro-signals and dynamic signatures for person authentication.Sensors2019;19:4641

[35] Zeynali M.EEG-based single-channel authentication systems with optimum electrode placement for different mental activities.Biomed J2019;42:261-7

[36] Seha SNA.EEG-based human recognition using steady-state AEPs and subject-unique spatial filters.IEEE Trans Inf Forensics Secur2020;15:3901-10

[37] Rathi N,Tiwari S.A novel approach for designing authentication system using a picture based P300 speller.Cogn Neurodyn2021;15:805-24

[38] Yap HY,Mohd Yusoh ZI.An evaluation of transfer learning models in EEG-based authentication.Brain Inform2023;10:19 PMCID:PMC10400490

[39] Alsumari W,Alshehri L.EEG-based person identification and authentication using deep convolutional neural network.Axioms2023;12:74

[40] Ferdi AY.Authentication with a one-dimensional CNN model using EEG-based brain-computer interface.Comput Methods Biomech Biomed Eng2025;28:1969-80

[41] Bolouri S.An EEG-based user authentication system using event-related potentials and ensemble learning. In 2024 Cyber Awareness and Research Symposium (CARS), Grand Forks, USA, Oct 28-29, 2024. IEEE: 2024; p. 1-6.

[42] Gong Y,Zhang Y,Pang S.A unified deep learning-based EEG biometric authentication system for cross-session scenarios. In International Conference on Advanced Data Mining and Applications. Springer: 2024; pp. 48-62.

[43] Mishra AR,Saini R.Performance enhancement of EEG signatures for person authentication using CNN BiLSTM method.J Univ Comput Sci2024;30:1755-79

[44] Valdes-Sosa PA,Bosch-Bayard J.The Cuban Human Brain Mapping Project, a young and middle age population-based EEG, MRI, and cognition dataset.Sci Data2021;8:45 PMCID:PMC7865011

[45] Miltiadous A,Afrantou T.A dataset of scalp EEG recordings of Alzheimer’s disease, frontotemporal dementia and healthy subjects from routine EEG.Data2023;8:95

[46] Prado P,Gonzalez-Gomez R.The BrainLat project, a multimodal neuroimaging dataset of neurodegeneration from underrepresented backgrounds.Sci Data2023;10:889 PMCID:PMC10710425

[47] Dzianok P.PEARL-Neuro Database: EEG, fMRI, health and lifestyle data of middle-aged people at risk of dementia.Sci Data2024;11:276

[48] Chu C,Song Z.An enhanced EEG microstate recognition framework based on deep neural networks: an application to Parkinson’s disease.IEEE J Biomed Health Inform2023;27:1307-18

[49] Antonova E,Suen HC,Maex R.EEG microstates: functional significance and short-term test-retest reliability.Neuroimage Rep2022;2:100089 PMCID:PMC12172836

[50] Nguyen QT.Standardising number of EEG sensors for AI-driven dementia detection.IEEE Sens Lett2025;9:1-4

[51] Nguyen QT,Tran XT et al.Transforming brainwaves into language: EEG microstates meet text embedding models for dementia detection. In The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria. Association for Computational Linguistics: 2025; pp. 186-202.

[52] Tarailis P,Michel CM.The functional aspects of resting EEG microstates: a systematic review.Brain Topogr2024;37:181-217

[53] Khanna A,Farzan F.Reliability of resting-state microstate features in electroencephalography.PloS One2014;9:e114163 PMCID:PMC4257589

[54] Koenig T,Stein M.Ragu: a free tool for the analysis of EEG and MEG event-related scalp field data using global randomization statistics.Comput Intell Neurosci2011;2011:938925 PMCID:PMC3049349

[55] Pascual-Marqui RD,Lehmann D.Segmentation of brain electrical activity into microstates: model estimation and validation.IEEE Trans Biomed Eng1995;42:658-65

[56] Bagdasarov A,Bréchet L,Michel CM.Spatiotemporal dynamics of EEG microstates in four-to eight-year-old children: age-and sex-related effects.Dev Cogn Neurosci2022;57:101134 PMCID:PMC9301511

[57] Valt C,Berchio C.MEG microstates: an investigation of underlying brain sources and potential neurophysiological processes.Brain Topogr2024;37:993-1009 PMCID:PMC11408537

[58] Zhao X,Zhao C,Wang C.Distraction-level recognition based on stacking ensemble learning for IVIS secondary tasks.Expert Syst Appl2024;244:122849

[59] Vaswani A,Parmar N. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, USA, Dec 4-9, 2017. 2017; pp. 5998-6008. https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html. (accessed 2026-06-25)

[60] LeCun Y,Hinton G.Deep learning.Nature2015;521:436-44

[61] Yan M,Bienstman P,Lin W.Emerging opportunities and challenges for the future of reservoir computing.Nat Commun2024;15:2056 PMCID:PMC10917819

[62] Wootton AJ,Day CR.Optimizing echo state networks for static pattern recognition.Cogn Comput2017;9:391-9

[63] Amin E,Zahran MA.Alzheimer’s disease: new insight in assessing of amyloid plaques morphologies using multifractal geometry based on Naive Bayes optimized by random forest algorithm.Sci Rep2023;13:18568 PMCID:PMC10616199

[64] Yuan Y,Guo Q,Shen C. Does ChatGPT know that it does not know? Evaluating the black-box calibration of ChatGPT. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). ELRA and ICCL: 2024; pp. 5191-201. https://aclanthology.org/2024.lrec-main.462/. (accessed 2026-06-25)

[65] Caton S.Fairness in machine learning: a survey.ACM Comput Surv2024;56:1-38

[66] Pessach D.A review on fairness in machine learning.ACM Comput Surv2022;55:1-44

[67] Férat V,Brunet D,Michel C.Pycrostates: a Python library to study EEG microstates.J Open Source Softw2022;7:4564

[68] Fisher RA. Statistical methods for research workers. 1934. https://archive.org/details/in.ernet.dli.2015.205971. (accessed 2026-06-25)

[69] Stouffer SA,DeVinney LC,Williams RM. The American soldier: adjustment during army life. 1949. https://gwern.net/doc/psychology/1949-stouffer-theamericansoldier-v1-adjustmentduringarmylife.pdf. (accessed 2026-06-25)

[70] Goeman JJ.Multiple hypothesis testing in genomics.Stat Med2014;33:1946-78

[71] Vallat R.Pingouin: statistics in Python.J Open Source Softw2018;3:1026

[72] Cohen J.Statistical power analysis for the behavioral sciences. 2nd Edition. Routledge; 2013.

[73] Nguyen QT,Tazin T.Emotion recognition using text embedding models: wearable and wireless EEG without fixed EEG channel configurations. In Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery: 2025; pp. 476-88.

[74] Zeng Y,Yang K.EEG-based identity authentication framework using face rapid serial visual presentation with optimized channels.Sensors2018;19:6

[75] Ortega-Rodríguez J,Pereda E.Selection of the minimum number of EEG sensors to guarantee biometric identification of individuals.Sensors2023;23:4239 PMCID:PMC10181121

[76] Gorur K,Ozer Z.EEG-driven biometric authentication for investigation of fourier synchrosqueezed transform-ICA robust framework.Arab J Sci Eng2023;48:10901-23

[77] Vadher H,Nair A.EEG-based biometric authentication system using convolutional neural network for military applications.Secur Priv2024;7:e345