# MINT-Demo: Membership Inference Test Demonstrator

arXiv: https://arxiv.org/abs/2503.08332 · HTML: https://mlsanity.com/paper/2503.08332/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 11 Mar 2025.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 7 of 7)

- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations](https://mlsanity.com/paper/2305.19962/) (2023)
- [FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data](https://mlsanity.com/paper/2311.10476/) (2023)
- [Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics](https://mlsanity.com/paper/2402.09225/) (2024)
- [Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs](https://mlsanity.com/paper/2503.07384/) (2025)

## Built on by (most cited first, 3 of 3)

- [Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2](https://mlsanity.com/paper/2606.14748/) (2026)
- [Auditing Training Data in Domain-adapted LLMs: LoRA-MINT](https://mlsanity.com/paper/2606.06946/) (2026)
- [Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning](https://mlsanity.com/paper/2509.07879/) (2025)

## Abstract (arXiv)

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.