mlsanityData to 7 Oct 2026

Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics

arXiv 2402.09225 ↗First posted 14 Feb 2024cs.CV cs.AIcited by 12

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

Abstract (arXiv)

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).

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 55 of its 100 references that are in the map. First posted on arXiv 14 Feb 2024.

Builds on

55 of 100 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022User-Level Membership Inference Attack against Metric Embedding Learning4 Mar
  2. 2021Membership Inference Attacks From First Principles7 Dec
  3. 2021On the Importance of Difficulty Calibration in Membership Inference Attacks15 Nov
  4. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar
  5. 2021Membership Inference Attacks are Easier on Difficult Problems15 Feb

Other references · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  8. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  9. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  10. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  11. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  12. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
38 more
  1. 2019Dreaming to Distill: Data-free Knowledge Transfer via DeepInversioncited by 419
  2. 2014Understanding Deep Image Representations by Inverting Themcited by 399
  3. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 374
  4. 2020Label-Only Membership Inference Attackscited by 371
  5. 2015Understanding Neural Networks Through Deep Visualizationcited by 332
  6. 2017Certified Defenses for Data Poisoning Attackscited by 288
  7. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  8. 2020Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defensescited by 171
  9. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  10. 2016Deep Pyramidal Residual Networkscited by 163
  11. 2020Partial FC: Training 10 Million Identities on a Single Machinecited by 163
  12. 2020Membership Leakage in Label-Only Exposurescited by 156
  13. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  14. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
  15. 2021Sample and Computation Redistribution for Efficient Face Detectioncited by 86
  16. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  17. 2022Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FCcited by 73
  18. 2020Radioactive data: tracing through trainingcited by 67
  19. 2020Masked Face Recognition Dataset and Applicationcited by 66
  20. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  21. 2020SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learningcited by 50
  22. 2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variationscited by 49
  23. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  24. 2024How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainabilitycited by 33
  25. 2020Defending Model Inversion and Membership Inference Attacks via Prediction Purificationcited by 32
  26. 2023Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitmentcited by 32
  27. 2020InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometricscited by 31
  28. 2022Does CLIP Know My Face?cited by 19
  29. 2021A Survey of Privacy Vulnerabilities of Mobile Device Sensorscited by 18
  30. 2016Do We Really Need to Collect Millions of Faces for Effective Face Recognition?cited by 17
  31. 2022An Overview of Privacy-enhancing Technologies in Biometric Recognitioncited by 17
  32. 2023FACE-AUDITOR: Data Auditing in Facial Recognition Systemscited by 15
  33. 2021IFBiD: Inference-Free Bias Detectioncited by 11
  34. 2020Data and Model Dependencies of Membership Inference Attackcited by 10
  35. 2023Toward Face Biometric De-identification using Adversarial Examplescited by 8
  36. 20233D-Aware Adversarial Makeup Generation for Facial Privacy Protectioncited by 5
  37. 2017Inference-Based Similarity Search in Randomized Montgomery Domains for Privacy-Preserving Biometric Identificationcited by 3
  38. 2024Double Trouble? Impact and Detection of Duplicates in Face Image Datasetscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 4; 2026: 4.

12 papers.

  1. 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancycited by 38
  2. 2024Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Datacited by 13
  3. 2025PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)cited by 10
  4. 2024Do Parameters Reveal More than Loss for Membership Inference?cited by 9
  5. 2025Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMscited by 9
  6. 2026Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2cited by 6
  7. 2025MINT-Demo: Membership Inference Test Demonstratorcited by 3
  8. 2026Auditing Training Data in Domain-adapted LLMs: LoRA-MINTcited by 3
  9. 2025Balancing Tails when Comparing Distributions: Comprehensive Equity Index (CEI) with Application to Bias Evaluation in Operational Face Biometricscited by 2
  10. 2024Identity-Focused Inference and Extraction Attacks on Diffusion Modelscited by 1
  11. 2026Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Modelscited by 0
  12. 2026Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identificationcited by 0