Membership Inference Attacks

Also known as MIA

Overview

Membership inference attacks ask whether a particular record, person, or dataset contributed to a model’s training, helping assess privacy risks. Black-box attacks use outputs such as loss, confidence, or generated text, while white-box methods analyze gradients and internal representations; LiRA and RMIA are prominent reference-model approaches. Researchers apply these methods to language, vision, generative, recommender, and federated models, and study defenses including differential privacy, regularization, and limits on exposed signals. A central challenge is that results can change sharply with attacker access, distribution shift, and false-positive rates, so reliable audits must distinguish practical privacy risks from apparent attack success under unrealistic assumptions.

Latest papers

CardsList

125 papers14 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

  1. Quantifying Membership Inference Risks in Genomic Data Sharing: The Role of Attacker's Auxiliary Information

    Nov 13, 2026Maryam Ghasemian, Lynette Hammond Gerido, Erman AydayMembership Inference AttacksPrivacy Auditing

  2. XposedMIA: Exploiting Explainable Artificial Intelligence (XAI) for One-Shot Membership Inference Attacks

    Nov 9, 2026Omar Hamdache, Serdar Kara, Kıvanç Kuzey Dikici +4Membership Inference AttacksExplainable Artificial Intelligence

  3. A Theoretical Reduction From Membership Inference to Reconstruction Attacks Against Learners

    Nov 8, 2026Amnon Levi, Yuval DaganTraining Data Reconstruction AttacksStatistical Learning Theory

  4. Bayesian Low-Rank Posteriors for Scalable Membership Inference

    Nov 7, 2026Khanh Nguyen, Antonio Emanuele Cinà, Andrey Barsky +3Membership Inference Attacks

  5. Overview of the ImageCLEFmedical 2026 GANs task: Exploring fingerprint detection, privacy leakage, and synthetic medical image generation

    Nov 6, 2026Alexandra-Georgiana Andrei, Mihai Gabriel Constantin, Mihai Dogariu +8Synthetic Data GenerationGenerative Adversarial Networks

  6. Timing is Everything: Inferring Temporal Membership in Continually Updated Models

    Nov 4, 2026Jie Fu, Xiangpeng Deng, Yuan Hong +1Membership Inference AttacksPrivacy Leakage in Language Models

  7. Probing Local Conditional Fit for Diffusion Model Membership Inference

    Nov 2, 2026ByungHee Cha, Naoki Murata, Yuhta Takida +2Membership Inference AttacksDiffusion Models

  8. Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs

    Oct 29, 2026Fei Wang, Baochun Li, Bo LiMixture-of-Experts Language ModelsMemorization in Language Models

  9. A Simple Presentation of Robust Membership Inference Attacks

    Oct 27, 2026Renaud Gaucher, Ephraim Linder, Adam Smith +2Membership Inference Attacks

  10. Shift-aware score transport for privacy auditing without retraining

    Oct 22, 2026Yaohong Yang, Gauri Pradhan, Qi Chen +2Privacy AuditingCovariate Shift

  11. Automated screening of privacy risks in medical AI

    Oct 21, 2026Konstantinos Vrettos, Eleftherios Tzanis, Haridimos Kondylakis +3Membership Inference AttacksPrivacy-Preserving ML

  12. Reliable Estimation of Differential Privacy under Selection Bias

    Oct 19, 2026Valentin Dorseuil, Meenatchi Sundaram Muthu Selva Annamalai, Jamal Atif +2Privacy AuditingDifferential Privacy

  13. Frequency-Domain Membership Inference Does Not Beat Confidence Thresholding: A Band-Resolved Analysis of Why

    Oct 17, 2026Mohammad Zare, Pirooz ShmamsinejadbabakiMembership Inference Attacks

  14. SoK: Rethinking Membership Inference in Tabular Machine Learning

    Oct 13, 2026Cristina Pêra, Tânia Carvalho, Maxime Cordy +1Membership Inference AttacksTabular ML

  15. COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration

    Oct 12, 2026Damien Lo, Hong Kyu Lee, Ruixuan Liu +1Membership Inference AttacksLarge Vision-Language Models

  16. Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation

    Oct 8, 2026Yilong Yang, Wenzhuo Shang, Yule Liu +2LLM AuditingMembership Inference Attacks

  17. Power Side-Channel Membership Inference Attack on Embedded Machine Learning

    Oct 7, 2026Sahan Sanjaya, Prabhat MishraMembership Inference AttacksEdge ML

  18. Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD

    Oct 7, 2026Murat Bilgehan Ertan, Marten van DijkPrivacy AccountingRandom Reshuffling

  19. When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry

    Oct 7, 2026Yixin Tan, Jiayang Liu, Lu Sun +3Privacy Leakage in Language ModelsMembership Inference Attacks

  20. Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use

    Oct 4, 2026Shang Wang, Tianqing Zhu, Huajie Chen +3LLM Backdoor AttacksModel Extraction Attacks

  21. Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy

    Oct 2, 2026Kaushik Bhargav Sivangi, Fani DeligianniPersonalized Differential Privacy3D Human Pose Estimation

  22. Calibrating One-Round Membership Inference with Neighbors

    Sep 28, 2026Francesco Rita, Jie Zhang, Florian TramèrMembership Inference Attacks

  23. Leaky Students: Membership Inference against On-Policy Distillation

    Sep 27, 2026Zhexi Lu, Mingzhi Zhu, Stacy Patterson +1Membership Inference AttacksPrivacy Leakage in Language Models

  24. Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective

    Sep 18, 2026Chenye Ke, Zirui Liu, Qi Liu +4Membership Inference AttacksLLM Auditing

  25. Membership Inference via Pairwise Likelihood Ratios

    Sep 11, 2026Shengjie Niu, Zebin Yun, Yeheng Ge +1Membership Inference AttacksLikelihood Ratio Testing

  26. Predicting Privacy Leakage from Weight Spectral Density

    Sep 10, 2026Richard J. Preen, Jim SmithPrivacy AuditingMembership Inference Attacks