mlsanityData to 7 Oct 2026

Fundamental Limits of Membership Inference Attacks on Machine Learning Models

arXiv 2310.13786 ↗First posted 20 Oct 2023stat.ML cs.AI cs.LGcited by 4

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

Abstract (arXiv)

Membership inference attacks (MIA) can reveal whether a particular data point was part of the training dataset, potentially exposing sensitive information about individuals. This article provides theoretical guarantees by exploring the fundamental statistical limitations associated with MIAs on machine learning models at large. More precisely, we first derive the statistical quantity that governs the effectiveness and success of such attacks. We then theoretically prove that in a non-linear regression setting with overfitting learning procedures, attacks may have a high probability of success. Finally, we investigate several situations for which we provide bounds on this quantity of interest. Interestingly, our findings indicate that discretizing the data might enhance the learning procedure's security. Specifically, it is demonstrated to be limited by a constant, which quantifies the diversity of the underlying data distribution. We illustrate those results through simple simulations.

Key facts. Cited by 4 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 28 of its 49 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

28 of 49 references.

Closest ancestors · 6

Same direction, newest first

  1. 2022Provable Membership Inference Privacy12 Nov
  2. 2022Membership Inference Attacks and Generalization: A Causal Perspective18 Sep
  3. 2022Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models22 Aug
  4. 2022Bounding Membership Inference24 Feb
  5. 2021Membership Inference Attacks From First Principles7 Dec
  6. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 22

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  2. 2019Deep Leakage from Gradientscited by 1,004
  3. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  4. 2022Quantifying Memorization Across Neural Language Modelscited by 755
  5. 2023Extracting Training Data from Diffusion Modelscited by 723
  6. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  7. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 452
  8. 2019Gradient Descent Maximizes the Margin of Homogeneous Neural Networkscited by 308
  9. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  10. 2022Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Modelscited by 218
  11. 2020Information Leakage in Embedding Modelscited by 199
  12. 2020Directional convergence and alignment in deep learningcited by 172
10 more
  1. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  2. 2017Machine Learning Models that Remember Too Muchcited by 165
  3. 2022The Privacy Onion Effect: Memorization is Relativecited by 128
  4. 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 66
  5. 2021Measuring Data Leakage in Machine-Learning Models with Fisher Informationcited by 31
  6. 2022Gradient Methods Provably Converge to Non-Robust Networkscited by 27
  7. 2021Membership Inference Attacks on Deep Regression Models for Neuroimagingcited by 19
  8. 2022Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fanocited by 16
  9. 2021Bounding Information Leakage in Machine Learningcited by 11
  10. 2022Measuring Unintended Memorisation of Unique Private Features in Neural Networkscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attackscited by 4
  2. 2025Membership Inference Risks in Quantized Models: A Theoretical and Empirical Studycited by 3
  3. 2026A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attackscited by 0
  4. 2026FairNVT: Fair Classification via Noise Injection in Vision Transformerscited by 0