$$\mathsf {vUBM}$$: A Variational Universal Background Model for EEG-Based Person Authentication

EEG-based person authentication is an important means for modern biometrics. However EEG signals are well-known for small signal-to-noise ratio and have many factors of variation. These variations are caused by intrinsic factors, e.g. mental activity, mood, and health conditions, as well as extrinsic factors, e.g. sensor errors, electrode displacements, and user movements. These create complex variations of source signals going from inside our brain to the recording devices. We propose \(\mathsf {vUBM}\), a variational inference framework to learn a simple latent representation for complex data, facilitating authentication algorithms in the latent space. A variational universal background model is created for normalizing scores to further improve the performance. Extensive experiments show the advantages of our proposed framework.