mlsanityData to 14 Oct 2026

MINT-Demo: Membership Inference Test Demonstrator

arXiv 2503.08332 ↗First posted 11 Mar 2025cs.CV cs.AIcited by 3

On the map: LLM safety and security → Membership inference attacks

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.

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.

Builds on

7 of 13 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs10 Mar
  2. 2024Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics14 Feb

Other references · 5

  1. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  2. 2016Deep Pyramidal Residual Networkscited by 163
  3. 2020Partial FC: Training 10 Million Identities on a Single Machinecited by 163
  4. 2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variationscited by 49
  5. 2023FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Datacited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2cited by 7
  2. 2026Auditing Training Data in Domain-adapted LLMs: LoRA-MINTcited by 4
  3. 2025Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learningcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2026Membership Inference Test: Auditing Training Data in Object Classification Models
  2. 2026inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs
  3. 2022Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
  4. 2022Membership Inference via Backdooring
  5. 2022Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
  6. 2024Anonymity Unveiled: A Practical Framework for Auditing Data Use in Deep Learning Models
  7. 2025Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis
  8. 2021Membership Inference Attacks on Machine Learning: A Survey