FaceMINT : a library for gaining insights into biometric face recognition via mechanistic interpretability

Rot, Peter (author), Jutreša, Robert (author), Peer, Peter (author), Štruc, Vitomir (author), Scheirer, Walter J. (author), Grm, Klemen (author)

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.

• Language: English
• Keywords: face recognition, biometrics, mechanistic interpretability, sparse autoencoder, library
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2026
• Number of pages: 20 str.
• Numbering: Vol. 165, art. 105804
• PID: 20.500.12556/RUL-175964
• UDC: 004.93'1
• ISSN on article: 0262-8856
• DOI: 10.1016/j.imavis.2025.105804
• COBISS.SI-ID: 257243651
• Publication date in RUL: 14.11.2025

Record is a part of a journal

• Title: Image and vision computing
• Shortened title: Image vis. comput.
• Publisher: Butterworth Scientific
• ISSN: 0262-8856
• COBISS.SI-ID: 25590016

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: razpoznavanje obrazov, biometrija, interpretacija mehanizmov, redki samokodirniki, knjižnica

Projects

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: J2-50069
• Name: Interpretacija mehanizmov za razložljivo biometrično umetno inteligenco (MIXBAI)

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0250
• Name: Metrologija in biometrični sistemi