Membership Inference Attacks

Also known as MIA

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

116 papers15 papers in the last four weeks, up 25% on the four weeks before. 0.1% of all new papers.

A Simple Presentation of Robust Membership Inference Attacks
Oct 27, 2026Renaud Gaucher, Ephraim Linder, Adam Smith +2Membership Inference Attacks
CMAP, École Polytechnique, Inria. · Department of Computer Science, Boston University. · Khoury College of Computer Sciences, Northeastern University. +1
OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation
Oct 22, 2026Qi Li, Xinchao WangMembership Inference Attacks On-Policy Self-Distillation
National University of Singapore
Shift-aware score transport for privacy auditing without retraining
Oct 22, 2026Yaohong Yang, Gauri Pradhan, Qi Chen +2Privacy Auditing Covariate Shift
ELLIS Institute Finland · Department of Computer Science, Aalto University, Finland · Department of Computer Science, University of Helsinki, Finland +1
Automated screening of privacy risks in medical AI
Oct 21, 2026Konstantinos Vrettos, Eleftherios Tzanis, Haridimos Kondylakis +3Membership Inference Attacks Privacy-Preserving ML
Artificial Intelligence and Translational Imaging (ATI) Lab, Department of Radiology, School of Medicine, University of Crete, Heraklion, Crete, Greece · Division of Radiology, Department of Clinical Science Intervention and Technology (CLINTEC), Karolinska Institute, Huddinge, Sweden · Computer Science Department, University of Crete, Crete, Greece +4
Reliable Estimation of Differential Privacy under Selection Bias
Oct 19, 2026Valentin Dorseuil, Meenatchi Sundaram Muthu Selva Annamalai, Jamal Atif +2Privacy Auditing Differential Privacy
DI-ENS · UCL · CMAP +1
Frequency-Domain Membership Inference Does Not Beat Confidence Thresholding: A Band-Resolved Analysis of Why
Oct 17, 2026Mohammad Zare, Pirooz ShmamsinejadbabakiMembership Inference Attacks
Department of Computer Engineering and Information Technology, Shiraz University of Technology, Shiraz, Iran
SoK: Rethinking Membership Inference in Tabular Machine Learning
Oct 13, 2026Cristina Pêra, Tânia Carvalho, Maxime Cordy +1Membership Inference Attacks Tabular ML
TekPrivacy, Portugal · SnT, University of Luxembourg, Luxembourg · Department of Computer Science, Faculty of Sciences of the University of Porto, Portugal
COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration
Oct 12, 2026Damien Lo, Hong Kyu Lee, Ruixuan Liu +1Membership Inference Attacks Large Vision-Language Models
Department of Computer Science, Emory University, Atlanta, GA
Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation
Oct 8, 2026Yilong Yang, Wenzhuo Shang, Yule Liu +2LLM Auditing Membership Inference Attacks
Xidian University · Hong Kong University of Science and Technology (Guangzhou)
Power Side-Channel Membership Inference Attack on Embedded Machine Learning
Oct 7, 2026Sahan Sanjaya, Prabhat MishraMembership Inference Attacks Edge ML
Department of Computer & Information Science & Engineering, University of Florida, USA
Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGD
Oct 7, 2026Murat Bilgehan Ertan, Marten van DijkRandom Reshuffling Differentially Private Stochastic Gradient Descent
Affiliated with Vrije Universiteit Amsterdam.
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
Oct 7, 2026Yixin Tan, Jiayang Liu, Lu Sun +3Privacy Leakage in Language Models Membership Inference Attacks
Institute of Science Tokyo · Nanyang Technological University · Tohoku University +2
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
Oct 4, 2026Shang Wang, Tianqing Zhu, Huajie Chen +3LLM Backdoor Attacks Model Extraction Attacks
School of Computer Science, University of Technology Sydney, Sydney, Australia · Faculty of Data Science, City University of Macau, Macau, China
OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models
Oct 2, 2026Tao Shi, Chaoyi Xiang, Qiongkai Xu +1Membership Inference Attacks Privacy Leakage in Language Models
The University of Melbourne · Macquarie University
Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy
Oct 2, 2026Kaushik Bhargav Sivangi, Fani DeligianniPersonalized Differential Privacy 3D Human Pose Estimation
Bio-AIm Lab School of Computing Science University of Glasgow
Calibrating One-Round Membership Inference with Neighbors
Sep 28, 2026Francesco Rita, Jie Zhang, Florian TramèrMembership Inference Attacks
ETH Zurich Zurich, Switzerland
Leaky Students: Membership Inference against On-Policy Distillation
Sep 27, 2026Zhexi Lu, Mingzhi Zhu, Stacy Patterson +1Membership Inference Attacks Privacy Leakage in Language Models
Rensselaer Polytechnic Institute
Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective
Sep 18, 2026Chenye Ke, Zirui Liu, Qi Liu +4Membership Inference Attacks LLM Auditing
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics +1
Membership Inference via Pairwise Likelihood Ratios
Sep 11, 2026Shengjie Niu, Zebin Yun, Yeheng Ge +1Membership Inference Attacks Likelihood Ratio Testing
The Hong Kong Polytechnic University, Hong Kong, China · Tel Aviv University, Israel
Predicting Privacy Leakage from Weight Spectral Density
Sep 10, 2026Richard J. Preen, Jim SmithPrivacy Auditing Membership Inference Attacks
Department of Computer Science and Creative Technologies University of the West of England Bristol, UK BS16 1QY
Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2
Sep 10, 2026William Novak, Muhammad AbusaqerMembership Inference Attacks Privacy-Preserving ML
Minot State University
Subgroup Membership Inference Audits of Differentially Private Synthetic Text
Sep 9, 2026Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +2Privacy Auditing Membership Inference Attacks
Imperial College London, Imperial Global Singapore · Nanyang Technological University, Singapore · Imperial College London, United Kingdom
SoK: Privacy Attacks on Machine Learning via Explainable AI
Sep 9, 2026Abdullah Caglar Oksuz, Anisa Halimi, Erman AydayModel Extraction Attacks Model Inversion Attacks
Case Western Reserve University · IBM Research
Black-Box Membership Inference via Word-Level Probability Estimation
Sep 8, 2026Shengjie Niu, Yeheng Ge, Jian HuangMembership Inference Attacks Privacy Leakage in Language Models
Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University, Hong Kong SAR, China · Department of Applied Mathematics The Hong Kong Polytechnic University, Hong Kong SAR, China
Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks
Sep 8, 2026Jialu Guo, Xiao Han, Junjie WuPrivacy-Preserving ML Diffusion Models
MIIT Key Laboratory of Data Intelligence and Management Beihang University Beijing, China
Characterizing Privacy Risks of Quantum Machine Learning with Emergent Quantum-Native Access
Sep 4, 2026Liou Tang, James Joshi, Ashish KunduMembership Inference Attacks Quantum Machine Learning
University of Pittsburgh, Pittsburgh, PA, USA · Cisco Research, San Jose, CA, USA
Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Models
Sep 1, 2026Kunlin Cai, Kaiyuan Zhang, Zihang Xiang +4TTS Synthesis Membership Inference Attacks
University of California, Los Angeles · University of Tennessee, Knoxville
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Sep 1, 2026Shengfang Zhai, Leo Marchyok, Yuling Shi +4Memorization in Language Models Membership Inference Attacks
National University of Singapore · Oregon State University · Shanghai Jiao Tong University +1
FISGuard: Defending Against Membership Inference via Fixed Input Subspaces
Aug 28, 2026Haocheng Jiang, Hua ShenPrivacy-Preserving Language Models Membership Inference Attacks
Hubei University of Technology
Weak Ties, Strong Signals: Efficient Training Data Detection in Diffusion LLMs via Independent Token Sampling
Aug 26, 2026Hongyao Yu, Tianqu Zhuang, Ziyuan Xu +4Privacy Leakage in Language Models Membership Inference Attacks
Tsinghua University · Harbin Institute of Technology, Shenzhen

Oct 27, 2026J/K move · Enter open · S save

A Simple Presentation of Robust Membership Inference Attacks

Renaud Gaucher, Ephraim Linder, Adam Smith, Jonathan Ullman+1

CMAP, École Polytechnique, Inria. · Department of Computer Science, Boston University. · Khoury College of Computer Sciences, Northeastern University.+1

Membership Inference Attacks

Open paper AskPDF arXiv

In a membership inference attack, an attacker is given the data of a particular individual, and tries to determine if that individual was included in a particular dataset, given some kind of statistics derived from the dataset or a model trained on the dataset. Roughly, a membership inference attack is robust if it succeeds even when the statistics are highly noisy, regardless of how that noise is introduced. We give a simple presentation of robust membership inference attacks for mean estimation, covering both multivariate Gaussian distributions and binary product distributions. We also give a summary of the literature on robust membership inference, covering history, extensions, and connections to other research areas.