20.500.12556/RUL-175964 FaceMINT a library for gaining insights into biometric face recognition via mechanistic interpretability Deep-learning models, including those used in biometric recognition, have achieved remarkable performance on benchmark datasets as well as real-world recognition tasks. However, a major drawback of these models is their lack of transparency in decision-making. Mechanistic interpretability has emerged as a promising research field intended to help us gain insights into such models, but its application to biometric data remains limited. In this work, we bridge this gap by introducing the FaceMINT library, a publicly available Python library (build on top of Pytorch) that enables biometric researchers to inspect their models through mechanistic interpretability. It provides a plug-and-play solution that allows researchers to seamlessly switch between the analyzed biometric models, evaluate state-of-the-art sparse autoencoders, select from various image parametrizations, and fine-tune hyperparameters. Using a large scale Glint360K dataset, we demonstrate the usability of FaceMINT by applying its functionality to two state-of-the-art (deep-learning) face recognition models: AdaFace, based on Convolutional Neural Networks (CNN), and SwinFace, based on transformers. The proposed library implements various sparse auto-encoders (SAEs), including vanilla SAE, Gated SAE, JumpReLU SAE, and TopK SAE, which have achieved state-of-the-art results in the mechanistic interpretability of large language models. Our study highlights the promise of mechanistic interpretability in the biometric field, providing new avenues for researchers to explore model transparency and refine biometric recognition systems. The library is publicly available at www.gitlab.com/peterrot/facemint (http://www.gitlab.com/peterrot/facemint). face recognition biometrics mechanistic interpretability sparse autoencoder library razpoznavanje obrazov biometrija interpretacija mehanizmov redki samokodirniki knjižnica true false true Angleški jezik Slovenski jezik Članek v reviji 2025-11-14 12:35:00 2025-11-14 12:35:14 2026-07-07 04:17:34 0000-00-00 00:00:00 2026 0 0 20 str. art. 105804 Vol. 165 Jan. 2026 0000-00-00 Zaloznikova Objavljeno apc 0000-00-00 0000-00-00 0000-00-00 004.93'1 0262-8856 10.1016/j.imavis.2025.105804 257243651 1-s2.0-S0262885625003920-main.pdf 1-s2.0-S0262885625003920-main.pdf 1 F3E8C36E00F5253BBD22DF3B163F9E0D 37c3ab9980392c51792590ed9eca1c03443bea7318d6659de452f03c9099abe0 ce51fa3d-791d-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=237081 https://www.sciencedirect.com/science/article/pii/S0262885625003920 1 a7c7ab12-c14d-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=221956 Fakulteta za računalništvo in informatiko Fakulteta za elektrotehniko 0 0 0