mlsanityData to 14 Oct 2026

SoK: Rethinking Membership Inference in Tabular Machine Learning

arXiv 2610.18486 ↗First posted 13 Oct 2026cs.LGcited by 0

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

Abstract (arXiv)

Membership Inference Attacks (MIAs) are currently the dominant approach to evaluating privacy in machine learning applications. Despite their significance, several concerns remain unexplored, particularly with regard to tabular data. Existing evaluations focus predominantly on high-dimensional datasets, leaving the privacy behavior of small-to-medium datasets unexplored. In this paper, we present a new taxonomy for MIAs and conduct a comprehensive study of the factors influencing vulnerability. We evaluate four distinct state-of-the-art attacks across diverse tabular datasets and model architectures. Our results show that datasets with higher class granularity and majority class percentage are more susceptible to MIAs. We further demonstrate that advanced MIAs are highly dependent on adversarial knowledge of the target model, while reference model-free attacks often achieve statistically comparable results. Most importantly, we show that records with unique signatures (single-outs) remain highly vulnerable, even when common defenses are applied. These findings indicate that current defenses reduce average leakage, but fail to adequately protect the most sensitive individuals.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 52 of its 95 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

52 of 95 references.

Closest ancestors · 30

Same direction, newest first

  1. 2026Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries24 Jun
  2. 2025Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts15 Oct
  3. 2025Membership Inference Attacks on Recommender System: A Survey14 Sep
  4. 2025Imitative Membership Inference Attack8 Sep
  5. 2025Membership Inference Attack with Partial Features8 Aug
  6. 2025Membership Inference Attacks on Large-Scale Models: A Survey25 Mar
  7. 2025A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack13 Feb
  8. 2024Membership Inference Attacks Against In-Context Learning2 Sep
  9. 2024Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks31 Aug
  10. 2024Range Membership Inference Attacks9 Aug
  11. 2024SeqMIA: Sequential-Metric Based Membership Inference Attack21 Jul
  12. 2024Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability1 Jul
18 more
  1. 2024SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)25 Jun
  2. 2024Do Parameters Reveal More than Loss for Membership Inference?17 Jun
  3. 2024OSLO: One-Shot Label-Only Membership Inference Attacks27 May
  4. 2024GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation13 May
  5. 2024Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought11 May
  6. 2024Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning7 Feb
  7. 2023Low-Cost High-Power Membership Inference Attacks6 Dec
  8. 2023Scalable Membership Inference Attacks via Quantile Regression7 Jul
  9. 2023Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction4 Jul
  10. 2023Students Parrot Their Teachers: Membership Inference on Model Distillation6 Mar
  11. 2022Membership Inference Attacks by Exploiting Loss Trajectory31 Aug
  12. 2022Membership Inference Attack Using Self Influence Functions26 May
  13. 2021Membership Inference Attacks From First Principles7 Dec
  14. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  15. 2021On the Importance of Difficulty Calibration in Membership Inference Attacks15 Nov
  16. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture15 Oct
  17. 2021Membership Inference Attacks Against Recommender Systems16 Sep
  18. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 22

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  2. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  3. 2020Label-Only Membership Inference Attackscited by 388
  4. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  5. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  6. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 197
  7. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 186
  8. 2025TabArena: A Living Benchmark for Machine Learning on Tabular Datacited by 176
  9. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
  10. 2020Membership Leakage in Label-Only Exposurescited by 168
  11. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 112
  12. 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 90
10 more
  1. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 70
  2. 2019Diffprivlib: The IBM Differential Privacy Librarycited by 53
  3. 2021Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implicationscited by 52
  4. 2020On the Effectiveness of Regularization Against Membership Inference Attackscited by 24
  5. 2021Membership Inference Attacks on Deep Regression Models for Neuroimagingcited by 22
  6. 2022On the Privacy Effect of Data Enhancement via the Lens of Memorizationcited by 15
  7. 2021Membership Inference Attack and Defense for Wireless Signal Classifiers with Deep Learningcited by 5
  8. 2025SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversamplingcited by 4
  9. 2024Empowering Open Data Sharing for Social Good: A Privacy-Aware Approachcited by 3
  10. 2025SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Datacited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SoK: Challenges in Tabular Membership Inference Attacks
  2. 2026A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
  3. 2026A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
  4. 2025Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
  5. 2025Ensembling Membership Inference Attacks Against Tabular Generative Models
  6. 2022An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis Models
  7. 2024Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
  8. 2025Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis