Adversarial Deep Learning in EEG Biometrics

Overview

Journal IEEE Signal Process Lett

Date 2019 Dec 10

PMID 31814690

Citations 19

Authors

Ozan Ozdenizci

Ye Wang

Toshiaki Koike-Akino

Deniz Erdogmus

Affiliations

Soon will be listed here.

Abstract

Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG. Furthermore, recent methods have mostly trained and evaluated based on single session EEG data. We address this problem from an invariant representation learning perspective. We propose an adversarial inference approach to extend such deep learning models to learn session-invariant person-discriminative representations that can provide robustness in terms of longitudinal usability. Using adversarial learning within a deep convolutional network, we empirically assess and show improvements with our approach based on longitudinally collected EEG data for person identification from half-second EEG epochs.

Citing Articles

Threats and Mitigation Strategies for Electroencephalography-Based Person Authentication.

Unnisa Z, Tariq A, Din I, Shehzad D, Serhani M, Belkacem A Int J Telemed Appl. 2025; 2025:3946740.

PMID: 39949891 PMC: 11824856. DOI: 10.1155/ijta/3946740.

Joint disentangled representation and domain adversarial training for EEG-based cross-session biometric recognition in single-task protocols.

Liu H, Jin X, Liu D, Kong W, Tang J, Peng Y Cogn Neurodyn. 2025; 19(1):31.

PMID: 39866660 PMC: 11757832. DOI: 10.1007/s11571-024-10214-w.

Cross-session SSVEP brainprint recognition using attentive multi-sub-band depth identity embedding learning network.

Gu C, Jin X, Zhu L, Yi H, Liu H, Yang X Cogn Neurodyn. 2025; 19(1):15.

PMID: 39801915 PMC: 11717760. DOI: 10.1007/s11571-024-10192-z.

Harnessing Few-Shot Learning for EEG signal classification: a survey of state-of-the-art techniques and future directions.

Ahuja C, Sethia D Front Hum Neurosci. 2024; 18:1421922.

PMID: 39050382 PMC: 11266297. DOI: 10.3389/fnhum.2024.1421922.

Automated mood disorder symptoms monitoring from multivariate time-series sensory data: getting the full picture beyond a single number.

Corponi F, Li B, Anmella G, Mas A, Pacchiarotti I, Valenti M Transl Psychiatry. 2024; 14(1):161.

PMID: 38531865 PMC: 10965916. DOI: 10.1038/s41398-024-02876-1.

References

Cecotti H, Graser A . Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE Trans Pattern Anal Mach Intell. 2010; 33(3):433-45. DOI: 10.1109/TPAMI.2010.125. View

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

Palaniappan R, Mandic D . Biometrics from brain electrical activity: a machine learning approach. IEEE Trans Pattern Anal Mach Intell. 2007; 29(4):738-42. DOI: 10.1109/TPAMI.2007.1013. View

Marcel S, Millan J . Person authentication using brainwaves (EEG) and maximum a posteriori model adaptation. IEEE Trans Pattern Anal Mach Intell. 2007; 29(4):743-52. DOI: 10.1109/TPAMI.2007.1012. View

Ma L, Minett J, Blu T, Wang W . Resting State EEG-based biometrics for individual identification using convolutional neural networks. Annu Int Conf IEEE Eng Med Biol Soc. 2016; 2015:2848-51. DOI: 10.1109/EMBC.2015.7318985. View

Touyama H, Hirose M . Non-target photo images in oddball paradigm improve EEG-based personal identification rates. Annu Int Conf IEEE Eng Med Biol Soc. 2009; 2008:4118-21. DOI: 10.1109/IEMBS.2008.4650115. View

Koike-Akino T, Mahajan R, Marks T, Wang Y, Watanabe S, Tuzel O . High-accuracy user identification using EEG biometrics. Annu Int Conf IEEE Eng Med Biol Soc. 2017; 2016:854-858. DOI: 10.1109/EMBC.2016.7590835. View

Gonzalez-Navarro P, Moghadamfalahi M, Akcakaya M, Erdogmus D . Spatio-Temporal EEG Models for Brain Interfaces. Signal Processing. 2016; 131:333-343. PMC: 5047025. DOI: 10.1016/j.sigpro.2016.08.001. View

Das K, Zhang S, Giesbrecht B, Eckstein M . Using rapid visually evoked EEG activity for person identification. Annu Int Conf IEEE Eng Med Biol Soc. 2009; 2009:2490-3. DOI: 10.1109/IEMBS.2009.5334858. View

10.

Kwak N, Muller K, Lee S . A convolutional neural network for steady state visual evoked potential classification under ambulatory environment. PLoS One. 2017; 12(2):e0172578. PMC: 5321422. DOI: 10.1371/journal.pone.0172578. View

11.

Orhan U, Hild 2nd K, Erdogmus D, Roark B, Oken B, Fried-Oken M . RSVP Keyboard: An EEG Based Typing Interface. Proc IEEE Int Conf Acoust Speech Signal Process. 2014; . PMC: 3771530. DOI: 10.1109/ICASSP.2012.6287966. View

12.

Lawhern V, Solon A, Waytowich N, Gordon S, Hung C, Lance B . EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces. J Neural Eng. 2018; 15(5):056013. DOI: 10.1088/1741-2552/aace8c. View

13.

Sakhavi S, Guan C, Yan S . Learning Temporal Information for Brain-Computer Interface Using Convolutional Neural Networks. IEEE Trans Neural Netw Learn Syst. 2018; 29(11):5619-5629. DOI: 10.1109/TNNLS.2018.2789927. View

14.

DelPozo-Banos M, Travieso C, Weidemann C, Alonso J . EEG biometric identification: a thorough exploration of the time-frequency domain. J Neural Eng. 2015; 12(5):056019. DOI: 10.1088/1741-2560/12/5/056019. View

15.

Schirrmeister R, Springenberg J, Fiederer L, Glasstetter M, Eggensperger K, Tangermann M . Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp. 2017; 38(11):5391-5420. PMC: 5655781. DOI: 10.1002/hbm.23730. View