AuthFormer: Adaptive Multimodal biometric authentication transformer for middle-aged and elderly people

TL;DR

An adaptive multimodal biometric authentication model, AuthFormer, tailored for elderly users, that improves adaptability to physiological variations in elderly users and requires only two layers to perform optimally, reducing complexity compared to traditional Transformer-based models.

Abstract

Multimodal biometric authentication methods address the limitations of unimodal biometric technologies in security, robustness, and user adaptability. However, most existing methods depend on fixed combinations and numbers of biometric modalities, which restricts flexibility and adaptability in real-world applications. To overcome these challenges, we propose an adaptive multimodal biometric authentication model, AuthFormer, tailored for elderly users. AuthFormer is trained on the LUTBIO multimodal biometric database, containing biometric data from elderly individuals. By incorporating a cross-attention mechanism and a Gated Residual Network (GRN), the model improves adaptability to physiological variations in elderly users. Experiments show that AuthFormer achieves an accuracy of 99.73%. Additionally, its encoder requires only two layers to perform optimally, reducing complexity compared to traditional Transformer-based models.

Figures (2)

• Figure 1: The left side of the figure shows the framework of AuthFormer, while the right side displays the biometric modalities (a) and subject age distribution (b) included in the LUTBIO multimodal biometric database.
• Figure 2: Comparison of accuracy and time consumption for different encoder layers.