AI Governance Engineer
GitHub

Membership inference

By Updated

An attack that determines whether a specific person's record was in a model's training set from the model's behaviour 1. The EDPB counts resistance to it among the evidence for claiming a model is anonymous.

Developed in
ch. 19, AI-specific privacy breaches
Chapters
ch. 19, Privacy & AI
Contrast with
Model inversion
Source
1 numbered reference, listed below

Where it is used

3 chapters of the Body of Knowledge use the term. Each link opens the first section that does.

Patterns that use this term

One pattern page uses the term.

  • Personal data breach

    A breach of security leading to the accidental or unlawful destruction, loss, alteration or unauthorised disclosure of, or access to, personal data, notified…

  • Regurgitation

    A model reproducing memorised training data verbatim, including personal data, whether prompted deliberately (training-data extraction) or not.

Sources

  1. [1] "Membership Inference Attacks against Machine Learning Models" (Shokri et al.; arXiv 1610.05820). arXiv. 2016-10-18. https://arxiv.org/abs/1610.05820 (verified: primary)

Definitions of legal terms paraphrase the cited text, which governs. Dated statements are as of .

Cite this term

García Aibar, J. (2026). Membership inference. In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0), Glossary. https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/glossary/membership-inference. CC BY 4.0

BibTeX

@misc{aige2026membershipinference,
  author  = {Jorge García Aibar},
  title   = {{Membership inference}},
  note    = {Glossary, AI Governance Engineering: The Thesis \& Body of Knowledge, version 0.5.0},
  year    = {2026},
  doi     = {10.5281/zenodo.22956197},
  url     = {https://aigovernanceengineer.com/glossary/membership-inference}
}