Finger Vein Spoof GANs: Issues in Presentation Attack Detector Training
Andreas Vorderleitner, Andreas Uhl · 2025
Four GAN-based I2I translation techniques for unpaired data are employed for the synthesis of biometric finger vein presentation attack instrument (PAI) samples corresponding to three public presentation attack datasets. These synthetic samples are used to train presentation attack detectors (PAD) using distinct feature sets in their classifier. We aim to assess the usefulness of these synthetic data for augmenting PAI datasets, and our analysis reveals that CycleGAN generated PAI samples are best suited to train PAD while DRIT generated data are hardly suited at all. This result corresponds well to visual appearance and quality measures of the synthetic PAI samples. However, it turns out that different types of features used in PAD can lead to very different behaviour of the PAD system trained with synthetic data. For example, Fourier or LBP feature sets must not be used as these respond more to the embedded GAN model fingerprints than to visual similarity of synthetic and real PAI samples. On the other hand, pre-trained neural network features, Haralick features, and surprisingly, also simple features like histograms or localised variance and entropy can be used in the PAD system and lead to stable PAI sample detection results across all datasets and GAN-types (except DRIT) considered. Consequently, results indicate which synthesis technique / feature extraction scheme combinations should be considered when augmenting real PAI samples with synthetic ones in PAD training, and which combinations should be avoided.