Skip to content
AI News HubLIVE
Original source2 min read

Automated screening of privacy risks in medical AI

Summary

A new arXiv paper argues that privacy risk in medical AI models, usually reported as a cohort average, can hide severe exposure for individual patients. The authors measured per-patient membership inference risk across 7,789 models trained on six clinical datasets in four modalities and found that the highest-risk patients largely stay the same regardless of training configuration. They propose a lightweight four-model screening tool to flag vulnerable patients before production-model training.

SourcearXiv Machine LearningAuthor: Konstantinos Vrettos, Eleftherios Tzanis, Haridimos Kondylakis, Evangelia E. Vassalou, Florence X. Doo, Michail E. Klontzas
Automated screening of privacy risks in medical AI
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 21 Oct 2026]

Title:Automated screening of privacy risks in medical AI

View a PDF of the paper titled Automated screening of privacy risks in medical AI, by Konstantinos Vrettos and 5 other authors

View PDF

Abstract:Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the patients who contributed them. However, a model can reveal whether a patient's records were used in training, a privacy breach known as a membership inference attack. This risk is usually reported as a cohort average, which can appear negligible while individual patients are almost certainly exposed. Identifying potentially vulnerable records before developing a production model could make privacy assessment more practical. We measured each patient's vulnerability to membership inference attack, across 7,789 models trained on six clinical datasets in four modalities, including two adapted pretrained medical models. Training choices changed how many patients had high attack scores, but the patients who ranked highest by risk largely stayed the same across the configurations we tested. Stronger weight decay reduced the exposed cohort up to threefold, yet largely the same patients remained most at risk across training recipes, architectures and initializations, including foundation models. Therefore, we developed a lightweight screening tool that uses four small models to identify patients with high risk of exposure before production-model training. We also assessed if flagged patients could be protected without removing their data. Privacy screening should become incorporated into data preparation for clinical AI.

Comments: 37 pages, 5 figures

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)

Cite as: arXiv:2610.30229 [cs.LG]

(or arXiv:2610.30229v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.30229

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Michail Klontzas [view email] [v1] Wed, 21 Oct 2026 17:52:43 UTC (3,079 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Automated screening of privacy risks in medical AI, by Konstantinos Vrettos and 5 other authors

View PDF

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-10

Change to browse by:

cs cs.AI cs.CR

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Researchers measured per-patient membership inference risk across 7,789 models trained on six clinical datasets in four modalities
  • Cohort-average risk can look negligible while individual patients are almost certainly exposed
  • Stronger weight decay reduced the exposed cohort up to threefold, but the highest-risk patients largely remained the same
  • The proposed screening tool uses four small models to flag high-risk patients before production-model training

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models