This paper introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if specific data was used during the training of Artificial Intelligence (AI) models. Specifically, we propose two novel MINT architectures designed to learn the distinct activation patterns that emerge when an audited model is exposed to data used during its training process. The first architecture is based on a Multilayer Perceptron (MLP) network and the second one is based on Convolutional Neural Networks (CNNs). The proposed MINT architectures are evaluated on a challenging face recognition task, considering three state-of-the-art face recognition models. Experiments are carried out using six publicly available databases, comprising over 22 million face images in total. Also, different experimental scenarios are considered depending on the context available of the AI model to test. Promising results, up to 90% accuracy, are achieved using our proposed MINT approach, suggesting that it is possible to recognize if an AI model has been trained with specific data.

翻译：本文提出成员推理测试（MINT）这一新方法，旨在通过实验判断特定数据是否被用于人工智能（AI）模型的训练过程。具体而言，我们设计了两种新型MINT架构，用于学习被审计模型在接触训练数据时产生的独特激活模式。第一种架构基于多层感知器（MLP）网络，第二种基于卷积神经网络（CNN）。所提出的MINT架构在具有挑战性的人脸识别任务上进行了评估，考虑了三种当前最优的人脸识别模型。实验使用了六个公开数据库，总计超过2200万张人脸图像。此外，根据待测试AI模型可获得的不同上下文信息，还设计了多种实验场景。我们的MINT方法取得了高达90%准确率的优异结果，表明能够识别AI模型是否使用了特定数据进行训练。