mlsanityData to 14 Oct 2026

Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2

arXiv 2606.14748 ↗First posted 5 Jun 2026cs.CV cs.AIcited by 7

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

Abstract (arXiv)

We present the Membership Inference Test (MINT) Demo 2, a framework designed to improve transparency in machine learning training processes. MINT is a technique for experimentally determining whether specific data were used during machine learning model training. We establish the theoretical framework and propose multiple architectures for MINT depending on the amount of information known about the models that are being audited. Experimental results using a popular face recognition model, 4 state-of-the-art LLMs, and multiple, diverse, and large-scale public image and text databases achieve promising accuracy levels in the detection of training data of up to 90%. Building on these results, we introduce a comprehensive web platform1 that expands these capabilities to image and text modalities. The platform integrates a diverse technological stack, including MINT, aMINT, and gMINT, allowing users to audit a wide range of models. This demonstrator aims to promote AI transparency and provides a practical tool to foster compliance with emerging AI regulations.

Key facts. Cited by 7 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 25 of its 42 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

25 of 42 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning9 Sep
  2. 2025MINT-Demo: Membership Inference Test Demonstrator11 Mar
  3. 2025Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs10 Mar
  4. 2024Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics14 Feb
  5. 2022Membership Inference Attacks by Exploiting Loss Trajectory31 Aug
  6. 2021Membership Inference Attacks From First Principles7 Dec
  7. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 18

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Qwen Technical Reportcited by 3,344
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  5. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  6. 2024Phi-4 Technical Reportcited by 711
  7. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  8. 2023Detecting Pretraining Data from Large Language Modelscited by 387
  9. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  10. 2024HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMscited by 265
  11. 2016Deep Pyramidal Residual Networkscited by 163
  12. 2020Partial FC: Training 10 Million Identities on a Single Machinecited by 163
6 more
  1. 2024Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Modelscited by 103
  2. 2023Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitmentcited by 33
  3. 2020InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometricscited by 31
  4. 2019SensitiveNets: Learning Agnostic Representations with Application to Face Imagescited by 18
  5. 2024Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Datacited by 13
  6. 2025Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitmentcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyondcited by 4
  2. 2026AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanationscited by 3
  3. 2026Comparative Study of Domain-adapted VLMs for General Document Visual Question Answeringcited by 3
  4. 2026CrimeNER Demo: Named-Entity Recognition in the Crime Domaincited by 0
  5. 2026AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanationscited by 0
  6. 2026VideoRun2D Demo: Markerless Body Tracking for Biomechanical Analysis of Runningcited by 0
  7. 2026inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Membership Inference Test: Auditing Training Data in Object Classification Models
  2. 2026Auditing Training Data in Domain-adapted LLMs: LoRA-MINT
  3. 2025Revisiting Data Auditing in Large Vision-Language Models
  4. 2024Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
  5. 2022Membership Inference via Backdooring
  6. 2024Membership Inference Attacks against Large Vision-Language Models
  7. 2025Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis
  8. 2022Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries