Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics
This addresses privacy and fairness concerns in AI by enabling detection of sensitive data usage in training, though it is incremental as it builds on existing membership inference concepts.
The authors tackled the problem of determining if specific data was used to train AI models by introducing the Membership Inference Test (MINT), achieving up to 90% accuracy in experiments on face recognition systems with over 22 million images.
This article introduces the Membership Inference Test (MINT), a novel approach that aims to empirically assess if given data was used during the training of AI/ML models. Specifically, we propose two MINT architectures designed to learn the distinct activation patterns that emerge when an Audited Model is exposed to data used during its training process. These architectures are based on Multilayer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs). The experimental framework focuses on the challenging task of Face Recognition, considering three state-of-the-art Face Recognition systems. Experiments are carried out using six publicly available databases, comprising over 22 million face images in total. Different experimental scenarios are considered depending on the context of the AI model to test. Our proposed MINT approach achieves promising results, with up to 90\% accuracy, indicating the potential to recognize if an AI model has been trained with specific data. The proposed MINT approach can serve to enforce privacy and fairness in several AI applications, e.g., revealing if sensitive or private data was used for training or tuning Large Language Models (LLMs).