mlsanityData to 7 Oct 2026

On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models

arXiv 2210.16258 ↗First posted 28 Oct 2022cs.CR cs.AIcited by 2

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

Abstract (arXiv)

Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data points as members or non-members of the training data. Intuitively, data points that MIA accurately detects are vulnerable. Considering those data points may exist in different target models susceptible to multiple MIAs, the vulnerability of data points under multiple MIAs and target models is worth exploring. This paper defines new metrics that can reflect the actual situation of data points' vulnerability and capture vulnerable data points under multiple MIAs and target models. From the analysis, MIA has an inference tendency to some data points despite a low overall inference performance. Additionally, we implement 54 MIAs, whose average attack accuracy ranges from 0.5 to 0.9, to support our analysis with our scalable and flexible platform, Membership Inference Attacks Platform (VMIAP). Furthermore, previous methods are unsuitable for finding vulnerable data points under multiple MIAs and different target models. Finally, we observe that the vulnerability is not characteristic of the data point but related to the MIA and target model.

Key facts. Cited by 2 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 30 of its 58 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

30 of 58 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members2 Mar
  2. 2021Membership Inference Attacks From First Principles7 Dec
  3. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov
  4. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models4 Feb

Other references · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  7. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  8. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  9. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  10. 2020Label-Only Membership Inference Attackscited by 371
  11. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  12. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
14 more
  1. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  2. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  3. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  4. 2020Membership Leakage in Label-Only Exposurescited by 156
  5. 2018Stealing Hyperparameters in Machine Learningcited by 115
  6. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108
  7. 2020On the Privacy Risks of Algorithmic Fairnesscited by 82
  8. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  9. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  10. 2020ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learningcited by 66
  11. 2021Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implicationscited by 50
  12. 2019Disparate Vulnerability to Membership Inference Attackscited by 33
  13. 2021SHAPr: An Efficient and Versatile Membership Privacy Risk Metric for Machine Learningcited by 10
  14. 2020SUOD: Toward Scalable Unsupervised Outlier Detectioncited by 4

Built on by

Cited by year

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

2 papers.

  1. 2024Membership Privacy Evaluation in Deep Spiking Neural Networkscited by 3
  2. 2025SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generationcited by 1