mlsanityData to 14 Oct 2026

Membership Inference Attacks via Adversarial Examples

arXiv 2207.13572 ↗First posted 27 Jul 2022cs.LG cs.AI cs.CRcited by 2

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

Abstract (arXiv)

The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often include personal data which can represent a threat to privacy. Membership inference attacks are a novel direction of research which aims at recovering training data used by a learning algorithm. In this paper, we develop a mean to measure the leakage of training data leveraging a quantity appearing as a proxy of the total variation of a trained model near its training samples. We extend our work by providing a novel defense mechanism. Our contributions are supported by empirical evidence through convincing numerical experiments.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 42 of its 82 references that are in the map. First posted on arXiv 27 Jul 2022.

Builds on

42 of 82 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  8. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  10. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  11. 2016Concrete Problems in AI Safetycited by 1,642
  12. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
30 more
  1. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  2. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  3. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  4. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 596
  5. 2019Benign Overfitting in Linear Regressioncited by 549
  6. 2020Overfitting in adversarially robust deep learningcited by 506
  7. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 460
  8. 2014Learning Face Representation from Scratchcited by 453
  9. 2020Label-Only Membership Inference Attackscited by 388
  10. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  11. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  12. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  13. 2020Membership Leakage in Label-Only Exposurescited by 168
  14. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 158
  15. 2020Benign overfitting in ridge regressioncited by 153
  16. 2017Stein Variational Gradient Descent as Gradient Flowcited by 152
  17. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
  18. 2019Maximum Mean Discrepancy Gradient Flowcited by 127
  19. 2016The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentationcited by 122
  20. 2018Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolatecited by 99
  21. 2018Wireless Network Intelligence at the Edgecited by 92
  22. 2021Learning in High Dimension Always Amounts to Extrapolationcited by 66
  23. 2021A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentationcited by 41
  24. 2020How benign is benign overfitting?cited by 40
  25. 2021Towards an Understanding of Benign Overfitting in Neural Networkscited by 30
  26. 2021QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learningcited by 26
  27. 2022Leveraging Adversarial Examples to Quantify Membership Information Leakagecited by 19
  28. 2021DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbscited by 11
  29. 2020Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraintscited by 7
  30. 2022Statistical Depth Functions for Ranking Distributions: Definitions, Statistical Learning and Applicationscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2026The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samplescited by 4
  2. 2023Membership Inference Attacks on DNNs using Adversarial Perturbationscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2022Evaluating Membership Inference Through Adversarial Robustness
  2. 2025Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
  3. 2023Fundamental Limits of Membership Inference Attacks on Machine Learning Models
  4. 2022Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
  5. 2026A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
  6. 2024A Method to Facilitate Membership Inference Attacks in Deep Learning Models
  7. 2026A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
  8. 2022On the Privacy Effect of Data Enhancement via the Lens of Memorization