mlsanityData to 7 Oct 2026

SoK: Challenges in Tabular Membership Inference Attacks

arXiv 2601.15874 ↗First posted 22 Jan 2026cs.LGcited by 1

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

Abstract (arXiv)

Membership Inference Attacks (MIAs) are currently a dominant approach for evaluating privacy in machine learning applications. Despite their significance in identifying records belonging to the training dataset, several concerns remain unexplored, particularly with regard to tabular data. In this paper, first, we provide an extensive review and analysis of MIAs considering two main learning paradigms: centralized and federated learning. We extend and refine the taxonomy for both. Second, we demonstrate the efficacy of MIAs in tabular data using several attack strategies, also including defenses. Furthermore, in a federated learning scenario, we consider the threat posed by an outsider adversary, which is often neglected. Third, we demonstrate the high vulnerability of single-outs (records with a unique signature) to MIAs. Lastly, we explore how MIAs transfer across model architectures. Our results point towards a general poor performance of these attacks in tabular data which contrasts with previous state-of-the-art. Notably, even attacks with limited attack performance can still successfully expose a large portion of single-outs. Moreover, our findings suggest that using different surrogate models makes MIAs more effective.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 51 of its 102 references that are in the map. First posted on arXiv 22 Jan 2026.

Builds on

51 of 102 references.

Closest ancestors · 23

Same direction, newest first

  1. 2025Membership Inference Attacks on Recommender System: A Survey14 Sep
  2. 2025Membership Inference Attacks on Large-Scale Models: A Survey25 Mar
  3. 2025Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models26 Feb
  4. 2025A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack13 Feb
  5. 2024Membership Inference Attacks Against In-Context Learning2 Sep
  6. 2024Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks31 Aug
  7. 2024Range Membership Inference Attacks9 Aug
  8. 2024Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability1 Jul
  9. 2024SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)25 Jun
  10. 2024Do Parameters Reveal More than Loss for Membership Inference?17 Jun
  11. 2024GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation13 May
  12. 2024Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought11 May
11 more
  1. 2023Low-Cost High-Power Membership Inference Attacks6 Dec
  2. 2023Scalable Membership Inference Attacks via Quantile Regression7 Jul
  3. 2023Students Parrot Their Teachers: Membership Inference on Model Distillation6 Mar
  4. 2023Bounding Training Data Reconstruction in DP-SGD14 Feb
  5. 2022Membership Inference Attack Using Self Influence Functions26 May
  6. 2021Membership Inference Attacks From First Principles7 Dec
  7. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  8. 2021On the Importance of Difficulty Calibration in Membership Inference Attacks15 Nov
  9. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture15 Oct
  10. 2021Membership Inference Attacks Against Recommender Systems16 Sep
  11. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  3. 2020Label-Only Membership Inference Attackscited by 371
  4. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  5. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  6. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  7. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  8. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  9. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  10. 2020Membership Leakage in Label-Only Exposurescited by 156
  11. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108
  12. 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 83
16 more
  1. 2017Knock Knock, Who's There? Membership Inference on Aggregate Location Datacited by 63
  2. 2022Vertical Federated Learning: Challenges, Methodologies and Experimentscited by 55
  3. 2021Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implicationscited by 50
  4. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  5. 2021Source Inference Attacks in Federated Learningcited by 31
  6. 2022Amplifying Membership Exposure via Data Poisoningcited by 29
  7. 2024Membership Inference Attacks and Defenses in Federated Learning: A Surveycited by 27
  8. 2020On the Effectiveness of Regularization Against Membership Inference Attackscited by 22
  9. 2021Membership Inference Attacks on Deep Regression Models for Neuroimagingcited by 19
  10. 2023Efficient and Secure Federated Learning for Financial Applicationscited by 17
  11. 2021Efficient passive membership inference attack in federated learningcited by 14
  12. 2022On the Privacy Effect of Data Enhancement via the Lens of Memorizationcited by 14
  13. 2021Membership Inference Attack and Defense for Wireless Signal Classifiers with Deep Learningcited by 4
  14. 2022Differentially-Private Data Synthetisation for Efficient Re-Identification Risk Controlcited by 4
  15. 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learningcited by 4
  16. 2024Empowering Open Data Sharing for Social Good: A Privacy-Aware Approachcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queriescited by 0