mlsanityData to 7 Oct 2026

Leveraging Adversarial Examples to Quantify Membership Information Leakage

arXiv 2203.09566 ↗First posted 17 Mar 2022cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained model is a standard way of measuring the privacy risks induced by the model. We develop a novel approach to address the problem of membership inference in pattern recognition models, relying on information provided by adversarial examples. The strategy we propose consists of measuring the magnitude of a perturbation necessary to build an adversarial example. Indeed, we argue that this quantity reflects the likelihood of belonging to the training data. Extensive numerical experiments on multivariate data and an array of state-of-the-art target models show that our method performs comparable or even outperforms state-of-the-art strategies, but without requiring any additional training samples.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 34 of its 67 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

34 of 67 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
22 more
  1. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  3. 2016Adversarial examples in the physical worldcited by 1,762
  4. 2016Concrete Problems in AI Safetycited by 1,582
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2020Overfitting in adversarially robust deep learningcited by 504
  8. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  9. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  10. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2016YouTube-8M: A Large-Scale Video Classification Benchmarkcited by 324
  13. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  14. 2020Membership Leakage in Label-Only Exposurescited by 156
  15. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  16. 2016The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentationcited by 122
  17. 2020QEBA: Query-Efficient Boundary-Based Blackbox Attackcited by 103
  18. 2018Understanding Membership Inferences on Well-Generalized Learning Modelscited by 83
  19. 2017Towards Measuring Membership Privacycited by 27
  20. 2021Membership Inference Attacks are Easier on Difficult Problemscited by 16
  21. 2021Markpainting: Adversarial Machine Learning meets Inpaintingcited by 9
  22. 2020Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraintscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 5; 2025: 1; 2026: 4.

16 papers.

Sort:

By area:

  1. 2024SeqMIA: Sequential-Metric Based Membership Inference Attackcited by 19
  2. 2022On the Privacy Effect of Data Enhancement via the Lens of Memorizationcited by 14
  3. 2024Center-Based Relaxed Learning Against Membership Inference Attackscited by 4
  4. 2026The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samplescited by 4
  5. 2023SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmarkcited by 3
  6. 2024Representation Magnitude has a Liability to Privacy Vulnerabilitycited by 3
  7. 2022Membership Inference Attacks via Adversarial Examplescited by 2
  8. 2023Disposable Transfer Learning for Selective Source Task Unlearningcited by 2
  9. 2024Inference Attacks: A Taxonomy, Survey, and Promising Directionscited by 2
  10. 2025Membership Inference Attacks with False Discovery Rate Controlcited by 2
  11. 2023Membership inference attack with relative decision boundary distancecited by 1
  12. 2023Membership Inference Attacks on DNNs using Adversarial Perturbationscited by 1
4 more
  1. 2026Decoupling Generalizability and Membership Privacy Risks in Neural Networkscited by 1
  2. 2024Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-trainingcited by 0
  3. 2026LeakBoost: Perceptual-Loss-Based Membership Inference Attackcited by 0
  4. 2026Learnability and Privacy Vulnerability are Entangled in a Few Critical Weightscited by 0