Membership inference vulnerability and the mitigating influence of regularization and differential privacy in dental radiograph classifiers
SAP Artificial Intelligence in Dentistry · 25.09.2026 · 2 · 153
DOI: 10.62486/aid2026153 ↗Kurz gefasst
Fachartikel in der Zeitschrift SAP Artificial Intelligence in Dentistry, online erschienen am 25.09.2026. Verfasst von Teng He und 2 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Deep learning classifiers for dental panoramic radiographs are trained on patient images, and the privacy of that training data is rarely audited.
Methods
ResNet-18 features were extracted from 182 annotated teeth in the openly licensed DENTEX dataset and used to train a four-class diagnostic classifier under four configurations (a baseline, L2 weight decay, dropout, and differentially private stochastic gradient descent). Membership inference was mounted with loss- and confidence-threshold attacks and scored with the area under the receiver operating characteristic curve across ten 70/30 train/test splits.
Results
The baseline classifier was vulnerable, with a loss-based attack AUC of 0.648 (95% CI 0.62-0.68). L2 weight decay and dropout reduced the AUC only marginally, to 0.647 and 0.633, whereas differentially private training reduced it to 0.537 (95% CI 0.53-0.55) and brought the confidence-based attack to chance (0.499), while lowering test accuracy from 70.4% to 54.5%.
Conclusions
Dental radiograph classifiers leak membership information; conventional regularization offers little protection, whereas differential privacy substantially reduces the risk at the cost of accuracy.
Zitieren
APA
He, T., Long, W., & Xie, Y. (2026). Membership inference vulnerability and the mitigating influence of regularization and differential privacy in dental radiograph classifiers. SAP Artificial Intelligence in Dentistry, 2, 153. https://doi.org/10.62486/aid2026153
Vancouver
He T, Long W, Xie Y. Membership inference vulnerability and the mitigating influence of regularization and differential privacy in dental radiograph classifiers. SAP Artificial Intelligence in Dentistry. 2026;2:153. doi:10.62486/aid2026153
BibTeX
@article{He2026,
author = {He, Teng and Long, Wenya and Xie, Yingjuan},
title = {Membership inference vulnerability and the mitigating influence of regularization and differential privacy in dental radiograph classifiers},
journal = {SAP Artificial Intelligence in Dentistry},
year = {2026},
volume = {2},
pages = {153},
doi = {10.62486/aid2026153}
}
EUVIMED