GAN pretraining for deep convolutional autoencoders applied to Software-based Fingerprint Presentation Attack Detection

TL;DR

This paper introduces a novel approach using Wasserstein GAN pretraining for deep convolutional autoencoders to improve software-based fingerprint presentation attack detection, achieving promising results without attack samples.

Contribution

It presents a new transfer learning method employing Wasserstein GAN pretraining for autoencoders in fingerprint attack detection, with minimal training data and no attack samples.

Findings

Achieved an average classification error rate of 16.79%

Autoencoder weights pretrained with Wasserstein GAN can generate realistic fingerprint patches

Provided architectural guidelines for autoencoder design in this context

Abstract

The need for reliable systems to determine fingerprint presentation attacks grows with the rising use of the fingerprint for authentication. This work presents a new approach to single-class classification for software-based fingerprint presentation attach detection. The described method utilizes a Wasserstein GAN to apply transfer learning to a deep convolutional autoencoder. By doing so, the autoencoder could be pretrained and finetuned on the LivDet2021 Dermalog sensor dataset with only 1122 bona fide training samples. Without making use of any presentation attack samples, the model could archive an average classification error rate of 16.79%. The Wasserstein GAN implemented to pretrain the autoencoders weights can further be used to generate realistic-looking artificial fingerprint patches. Extensive testing of different autoencoder architectures and hyperparameters led to coarse architectural guidelines as well as multiple implementations which can be utilized for future work.