Fingerprint Image Generation Based on Attention-Based Deep Generative Adversarial Networks and Its Application in Deep Siamese Matching Model Security Validation

This study addresses the critical need to evaluate the security of deep learning models in fingerprint recognition systems, by testing their vulnerability to misidentification. While deep learning techniques have significantly advanced biometric authentication, the potential for misclassification and unauthorized access due to synthetic fingerprints has not been thoroughly investigated. To this end, we propose an enhanced Deep Convolutional Generative Adversarial Network (DCGAN) with attention mechanisms to generate realistic synthetic fingerprint images. These images are then used to test the robustness and security of a Siamese Network employed for fingerprint matching. Experimental results demonstrate that the AE-DCGAN model outperforms traditional DCGANs in image quality and precision, achieving higher accuracy in generating realistic fingerprint textures. Additionally, the Siamese Network, when tested with synthetic fingerprints, reveals certain vulnerabilities, highlighting potential risks in security. Grad-CAM visualizations are employed to further understand the model's attention during fingerprint matching, providing insights into how the model focuses on key fingerprint features. The proposed approach aims to investigate both the generation and recognition phases, contributing to improved robustness and reliability in fingerprint-based systems.