Abstract
Silent speech is a convenient and natural way for person authentication as users can imagine speaking their password instead of typing it. However there are inherent noises and complex variations in EEG signals making it difficult to capture correct information and model uncertainty. We propose an EEG-based person authentication framework based on a variational inference framework to learn a simple latent representation for complex data. A variational universal background model is created by pooling the latent models of all users. A likelihood ratio of user claimed model to the background model is constructed for testing whether the claim is valid. Extensive experiments on three datasets show the advantages of our proposed framework.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Abdelfattah, S.M., Abdelrahman, G.M., Wang, M.: Augmenting the size of EEG datasets using generative adversarial networks. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE (2018)
Bashivan, P., Rish, I., Yeasin, M., Codella, N.: Learning representations from EEG with deep recurrent-convolutional neural networks. arXiv preprint arXiv:1511.06448 (2015)
Bishop, C.M.: Mixture Density Networks (1994)
Dai, M., Zheng, D., Na, R., Wang, S., Zhang, S.: EEG classification of motor imagery using a novel deep learning framework. Sensors 19(3), 551 (2019)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Lawhern, V.J., Solon, A.J., Waytowich, N.R., Gordon, S.M., Hung, C.P., Lance, B.J.: EEGNet: a compact convolutional neural network for eeg-based brain-computer interfaces. J. Neural Eng. 15(5), 056013 (2018)
Marcel, S., del R Millán, J.: Person authentication using brainwaves (EEG) and maximum a posteriori model adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 29(4), 743–752 (2007)
Nguyen, C.H., Karavas, G.K., Artemiadis, P.: Inferring imagined speech using EEG signals: a new approach using riemannian manifold features. J. Neural Eng. 15(1), 016002 (2017)
Nguyen, P., Tran, D., Le, T., Huang, X., Ma, W.: EEG-based person verification using multi-sphere SVDD and UBM. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) PAKDD 2013, Part I. LNCS (LNAI), vol. 7818, pp. 289–300. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37453-1_24
Ofner, P., Schwarz, A., Pereira, J., Müller-Putz, G.R.: Upper limb movements can be decoded from the time-domain of low-frequency EEG. PloS one 12(8), e0182578 (2017)
Pham, T., Ma, W., Tran, D., Nguyen, P., Phung, D.: Multi-factor EEG-based user authentication. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 4029–4034. IEEE (2014)
Reynolds, D.A.: Comparison of background normalization methods for text-independent speaker verification. In: Fifth European Conference on Speech Communication and Technology (1997)
Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted gaussian mixture models. Digit. Signal Process. 10(1–3), 19–41 (2000)
Schirrmeister, R.T., et al.: Deep learning with convolutional neural networks for EEG decoding and visualization. Hum. Brain Mapp. 38(11), 5391–5420 (2017)
Tran, D.T.: Fuzzy approaches to speech and speaker recognition. Ph.D. thesis, University of Canberra (2000)
Tran, N., Tran, D., Liu, S., Ma, W., Pham, T.: EEG-based person authentication system in different brain states. In: 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER), pp. 1050–1053. IEEE (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Appendix
A Appendix
1.1 A.1 KL Divergence Derivations
We state the first proposition without proof.
Proposition 3
Let \(f(x)=\mathcal {N}(x;\mu _{f},\varSigma _{f})\) and \(g(x)=\mathcal {N}(x;\mu _{g},\varSigma _{g})\) be two Gaussian distributions in \(\mathbb {R}^{n}.\) The Kullback-Leibler (KL) divergence between f(x) and g(x) is:
The following proposition provides the basis for the training objective of our proposed VGM model.
Proposition 4
The variational upper bound of the Kullback-Leibler divergence between a unimodal distribution f(x) and a mixture model \(g(x)=\sum _{k}\alpha _{k}g_{k}(x)\) is:
where \(D_{k}=\int f(x)\log \frac{f(x)}{g_{k}(x)}dx\) is the KL divergence between f(x) and \(g_{k}(x)\), the unimodal component distribution of the mixture g(x).
Proof
We have
where \(L_{f}=\int f(x)\log f(x)dx\) and \(L_{g}=\int f(x)\log \sum _{k}\alpha _{k}g_{k}(x)dx\), and the index k runs from 1 to K.
We will use variational method to lower bound \(L_{g}\). Let us introduce variational variables \(a_{1},\dots ,a_{K}\), with \(\sum _{k}a_{k}=1\), \(a_{k}>0\), \(k=1,\dots ,K\),
where we use Jenssen inequality in Eq. 21. We want to find the \(a_{k}\) that maximizes this lower bound. Since Eq. 21 is concave in each \(a_{k}\) it has a global maximum. Let take partial derivative of \(L'_{g}\) w.r.t. each \(a_{k}\) then set it to zero and let us denote \(D_{k}={D_{KL}}\left( f(x)\Vert g_{k}(x)\right) \) for brevity:
where we have used \(\int f(x)dx=1\) in Eq. 24.
From Eq. 26 and Eq. 28 we have:
Plug \(L'_{g}\) in Eq. 21 into Eq. 18:
where we substituted \(a_{k}=\frac{\alpha _{k}\exp \left( -D_{k}\right) }{Z}\) in Eq. 31 and move \(\log Z\) out of the integral in Eq. 32.
We will show that \(A=0\):
where we again used the facts that \(\int f(x)dx=1\) and \(\sum _{k}a_{k}=1\).
We have shown that \({D_{KL}}(f(x)\Vert g(x))\le L_{f}-L'_{g}=-\log Z\). \(\blacksquare \)
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Tran, H., Tran, D., Ma, W., Nguyen, P. (2019). EEG-Based Person Authentication with Variational Universal Background Model. In: Liu, J., Huang, X. (eds) Network and System Security. NSS 2019. Lecture Notes in Computer Science(), vol 11928. Springer, Cham. https://doi.org/10.1007/978-3-030-36938-5_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-36938-5_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36937-8
Online ISBN: 978-3-030-36938-5
eBook Packages: Computer ScienceComputer Science (R0)