MINT-Demo: Membership Inference Test Demonstrator

2025/03/11 by Daniel DeAlcala, DeAlcala, Daniel, Aythami Morales +9 · 1 citation
Computer Science · Decision Sciences · #Software System Performance and Reliability #Data Quality and Management #Scientific Computing and Data Management

paper · pdf · doi:10.48550/arxiv.2503.08332

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 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.

Cited by

• Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning

Related

• Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics
• Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning
• Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs
• Membership Inference Attacks are Easier on Difficult Problems
• Enhanced Membership Inference Attacks against Machine Learning Models