We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determining whether certain data has been used during the training of machine learning models. We conduct experiments with popular face recognition models and 5 public databases containing over 22M images. Promising results, up to 89% accuracy are achieved, suggesting that it is possible to recognize if an AI model has been trained with specific data. Finally, we present a MINT platform as demonstrator of this technology aimed to promote transparency in AI training.
@article{arxiv.2503.08332,
title = {MINT-Demo: Membership Inference Test Demonstrator},
author = {Daniel DeAlcala and Aythami Morales and Julian Fierrez and Gonzalo Mancera and Ruben Tolosana and Ruben Vera-Rodriguez},
journal= {arXiv preprint arXiv:2503.08332},
year = {2025}
}
Comments
Demo Paper Presented at Demo Track CVPR 24' and at AAAI 25' AIGOV workshop