MINT-Demo: Membership Inference Test Demonstrator

Daniel DeAlcala, Aythami Morales, Julian Fierrez, Gonzalo Mancera, Ruben Tolosana, Javier Ortega-Garcia

Keywords: Audit, Fairness, Reliability, Membership Inference, Face Recognition

TL;DR: We present the MINT, a technique for experimentally determining whether certain data has been used during the training of machine learning models to achive more transparent machine learning training processes.

Abstract: 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 $22$M images. Promising results, up to 89% accuracy, are achieved with our MINT approach, 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 (https://ai-mintest.org/).

Submission Number: 4