The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis

תקציר מקורי באנגליתarXiv:2601.19618v2 Announce Type: replace-cross Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is the strongest known remedy. Practice increasingly favors large generic self-supervised encoders. Yet the pretraining objective and the pretraining domain are confounded in existing comparisons, so which one preserves utility under privacy is unknown, and the pretraining corpus is treated as public even when it holds patient images. We trained ConvNeXt classifiers with differentially private stochastic gradient descent from five initializations that vary the objective and the domain independently, at four privacy budgets and without privacy, and evaluated them locally on more than 590,000