mlsanityData to 7 Oct 2026

A Blessing of Dimensionality in Membership Inference through Regularization

arXiv 2205.14055 ↗First posted 27 May 2022cs.LG stat.MLcited by 17

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

Abstract (arXiv)

Is overparameterization a privacy liability? In this work, we study the effect that the number of parameters has on a classifier's vulnerability to membership inference attacks. We first demonstrate how the number of parameters of a model can induce a privacy--utility trade-off: increasing the number of parameters generally improves generalization performance at the expense of lower privacy. However, remarkably, we then show that if coupled with proper regularization, increasing the number of parameters of a model can actually simultaneously increase both its privacy and performance, thereby eliminating the privacy--utility trade-off. Theoretically, we demonstrate this curious phenomenon for logistic regression with ridge regularization in a bi-level feature ensemble setting. Pursuant to our theoretical exploration, we develop a novel leave-one-out analysis tool to precisely characterize the vulnerability of a linear classifier to the optimal membership inference attack. We empirically exhibit this "blessing of dimensionality" for neural networks on a variety of tasks using early stopping as the regularizer.

Key facts. Cited by 17 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 37 of its 59 references that are in the map. First posted on arXiv 27 May 2022.

Builds on

37 of 59 references.

Closest ancestors · 8

Same direction, newest first

  1. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks8 Mar
  2. 2022Membership Inference Attacks and Defenses in Neural Network Pruning7 Feb
  3. 2022Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference2 Feb
  4. 2021Membership Inference Attacks From First Principles7 Dec
  5. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  6. 2021Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference11 Oct
  7. 2021The Influence of Dropout on Membership Inference in Differentially Private Models16 Mar
  8. 2021Membership Inference Attacks on Machine Learning: A Survey14 Mar

Other references · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  7. 2020Extracting Training Data from Large Language Modelscited by 2,144
  8. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  9. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 667
  10. 2017The Implicit Bias of Gradient Descent on Separable Datacited by 649
  11. 2019Benign Overfitting in Linear Regressioncited by 544
  12. 2019Surprises in High-Dimensional Ridgeless Least Squares Interpolationcited by 508
17 more
  1. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  2. 2019The generalization error of random features regression: Precise asymptotics and double descent curvecited by 410
  3. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  4. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  5. 2020Label-Only Membership Inference Attackscited by 371
  6. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  7. 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
  8. 2019Two models of double descent for weak featurescited by 194
  9. 2018To understand deep learning we need to understand kernel learningcited by 186
  10. 2019Gmail Smart Compose: Real-Time Assisted Writingcited by 97
  11. 2020Classification vs regression in overparameterized regimes: Does the loss function matter?cited by 97
  12. 2021A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learningcited by 54
  13. 2019The Impact of Regularization on High-dimensional Logistic Regressioncited by 35
  14. 2020Against Membership Inference Attack: Pruning is All You Needcited by 32
  15. 2020Generalization Error of Generalized Linear Models in High Dimensionscited by 25
  16. 2020Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (or : How to Prove Kabashima's Replica Formula)cited by 23
  17. 2020On the Effectiveness of Regularization Against Membership Inference Attackscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 2; 2026: 3.

17 papers.

Sort:

By area:

  1. 2024Deep Networks Always Grok and Here is Whycited by 49
  2. 2023Gaussian Membership Inference Privacycited by 20
  3. 2023Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networkscited by 9
  4. 2024GLiRA: Black-Box Membership Inference Attack via Knowledge Distillationcited by 6
  5. 2025Trustworthy AI: Safety, Bias, and Privacy -- A Surveycited by 5
  6. 2024Center-Based Relaxed Learning Against Membership Inference Attackscited by 4
  7. 2024Defending Membership Inference Attacks via Privacy-aware Sparsity Tuningcited by 4
  8. 2023Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Modelscited by 3
  9. 2023Training Dynamics of Deep Network Linear Regionscited by 3
  10. 2025A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attackcited by 2
  11. 2023Can sparsity improve the privacy of neural networks?cited by 1
  12. 2023Sparsity in neural networks can improve their privacycited by 1
5 more
  1. 2023Membership Inference Attacks on DNNs using Adversarial Perturbationscited by 1
  2. 2024The Impact of Generalization Techniques on the Interplay Among Privacy, Utility, and Fairness in Image Classificationcited by 1
  3. 2026Decoupling Generalizability and Membership Privacy Risks in Neural Networkscited by 1
  4. 2026Validity Threats for Foundation Model Researchcited by 0
  5. 2026Differential Privacy of Gaussian Process Posterior Samplingcited by 0