Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2
It addresses the need for transparency and regulatory compliance in AI by providing a practical tool to audit training data usage.
The paper presents the Membership Inference Test (MINT) framework to determine if specific data were used in training ML models, achieving up to 90% accuracy in detecting training data across face recognition models and LLMs.
We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes. MINT is a technique for experimentally determining whether specific data were used during machine learning model training. We establish the theoretical framework and propose multiple architectures for MINT depending on the amount of information known about the models that are being audited. Experimental results using a popular face recognition model, 4 state-of-the-art LLMs, and multiple, diverse, and large-scale public image and text databases achieve promising accuracy levels in the detection of training data of up to 90%. Building on these results, we introduce a comprehensive web platform1 that expands these capabilities to image and text modalities. The platform integrates a diverse technological stack, including MINT, aMINT, and gMINT, allowing users to audit a wide range of models. This demonstrator aims to promote AI transparency and provides a practical tool to foster compliance with emerging AI regulations.