CoChat

Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks

Open access
Mireshghallah, Fatemehsadat, Goyal, Kartik, Uniyal, Archit, Berg-Kirkpatrick, Taylor, Shokri, Reza · 2022 · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Cited by 92

The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.

Abstract

The wide adoption and application of Masked language models (MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities.Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying potential robustness of MLMs to privacy attacks.In this work, we posit that prior attempts were inconclusive because they based their attack solely on the MLM's model score.We devise a stronger membership inference attack based on likelihood ratio hypothesis testing that involves an additional reference MLM to more accurately quantify the privacy risks of memorization in MLMs.We show that masked language models are indeed susceptible to likelihood ratio membership inference attacks: Our empirical results, on models trained on medical notes, show that our attack improves the AUC of prior membership inference attacks from 0.66 to an alarmingly high 0.90 level.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2022.emnlp-main.570

Cites

16 of 16 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 16 references

Cited by

See all 92

Metadata

Authors
Mireshghallah, F., Goyal, K., Uniyal, A., Berg-Kirkpatrick, T., & Shokri, R.
Venue
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Published
2022
Pages
8332-8347
OpenAlex
W4385573947
Cited by
92
References
16
FWCI
10.18
Type
conference paper
Language
en
Open access
hybrid

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. https://app.cochat.ai/papers/10.18653/v1/2022.emnlp-main.570
The paper
Mireshghallah, F., Goyal, K., Uniyal, A., Berg-Kirkpatrick, T., & Shokri, R. (2022). Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2022.emnlp-main.570

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.