mlsanityData to 7 Oct 2026

Leakage of Dataset Properties in Multi-Party Machine Learning

arXiv 2006.07267 ↗First posted 12 Jun 2020cs.LG cs.CR stat.MLcited by 46

Not on the map. Why?

Abstract (arXiv)

Secure multi-party machine learning allows several parties to build a model on their pooled data to increase utility while not explicitly sharing data with each other. We show that such multi-party computation can cause leakage of global dataset properties between the parties even when parties obtain only black-box access to the final model. In particular, a ``curious'' party can infer the distribution of sensitive attributes in other parties' data with high accuracy. This raises concerns regarding the confidentiality of properties pertaining to the whole dataset as opposed to individual data records. We show that our attack can leak population-level properties in datasets of different types, including tabular, text, and graph data. To understand and measure the source of leakage, we consider several models of correlation between a sensitive attribute and the rest of the data. Using multiple machine learning models, we show that leakage occurs even if the sensitive attribute is not included in the training data and has a low correlation with other attributes or the target variable.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 14; 2023: 12; 2024: 10; 2025: 3; 2026: 5.

46 papers.

Sort:

By area:

  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  2. 2023FedFed: Feature Distillation against Data Heterogeneity in Federated Learningcited by 54
  3. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learningcited by 47
  4. 2021Formalizing and Estimating Distribution Inference Riskscited by 42
  5. 2023SoK: Memorization in General-Purpose Large Language Modelscited by 36
  6. 2022SNAP: Efficient Extraction of Private Properties with Poisoningcited by 29
  7. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  8. 2022Group Property Inference Attacks Against Graph Neural Networkscited by 21
  9. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
  10. 2022Distribution inference risks: Identifying and mitigating sources of leakagecited by 17
  11. 2022Inferring Sensitive Attributes from Model Explanationscited by 15
  12. 2022Dissecting Distribution Inferencecited by 15
34 more
  1. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 14
  2. 2024Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attackscited by 13
  3. 2024Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?cited by 13
  4. 2022Protecting Global Properties of Datasets with Distribution Privacy Mechanismscited by 11
  5. 2022Privacy Leakage in Text Classification: A Data Extraction Approachcited by 9
  6. 2021Correlation inference attacks against machine learning modelscited by 7
  7. 2022Combing for Credentials: Active Pattern Extraction from Smart Replycited by 7
  8. 2023Manipulating Transfer Learning for Property Inferencecited by 7
  9. 2025Detecting Data Contamination in LLMs via In-Context Learningcited by 7
  10. 2023Summary Statistic Privacy in Data Sharingcited by 6
  11. 2023Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Modelscited by 6
  12. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  13. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6
  14. 2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
  15. 2023Attesting Distributional Properties of Training Data for Machine Learningcited by 5
  16. 2023Privacy-preserving machine learning for healthcare: open challenges and future perspectivescited by 4
  17. 2025Can We Infer Confidential Properties of Training Data from LLMs?cited by 4
  18. 2022FedComm: Federated Learning as a Medium for Covert Communicationcited by 3
  19. 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approachcited by 3
  20. 2024Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learningcited by 2
  21. 2025Adversarial Robustness in Distributed Quantum Machine Learningcited by 2
  22. 2026Inference Attacks Against Graph Generative Diffusion Modelscited by 2
  23. 2022Lessons Learned: Defending Against Property Inference Attackscited by 1
  24. 2022Inferring Class Label Distribution of Training Data from Classifiers: An Accuracy-Augmented Meta-Classifier Attackcited by 1
  25. 2024Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemblecited by 1
  26. 2024FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learningcited by 1
  27. 2026Alignment Defends LLMs from Property Inference Attackscited by 1
  28. 2023Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomycited by 0
  29. 2023A Blackbox Model Is All You Need to Breach Privacy: Smart Grid Forecasting Models as a Use Casecited by 0
  30. 2024Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Themcited by 0
  31. 2024Survey of Privacy Threats and Countermeasures in Federated Learningcited by 0
  32. 2026SoK: Colluding Adversaries in Machine Learning Pipelinescited by 0
  33. 2026Code-Poisoning Property Inference Attackscited by 0
  34. 2026QuanText: Protecting Dataset-Level Secrets in Textual Data Sharingcited by 0