Membership inference vulnerability and the mitigating influence of regularization and differential privacy in dental radiograph classifiers

Teng He, Wenya Long and Yingjuan Xie

SAP Artificial Intelligence in Dentistry, 2026

Abstract: 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.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://southam.pub/journals/files/aid/aid2026153en.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cwf:aidart:aid2026153

DOI: 10.62486/aid2026153

Access Statistics for this article

More articles in SAP Artificial Intelligence in Dentistry from South American Publishing
Bibliographic data for series maintained by South American Publishing Journals Manager ().