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

arXiv:2601.19618 · cs.CV, cs.AI, cs.LG · Submitted 2026-01-27 · Read on arXiv

cs.CV, cs.AI, cs.LG

Submitted: 2026-01-27

Updated: 2026-10-10

Code: https://github.com/tayebiarasteh/dp_dinov3

Terminology

• Differentially Private — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Differential Privacy — 1× in this paper · explained in 4 episodes

Sources

• Unlocking High-Accuracy Differentially Private Image Classification through Scale
• Toward Training at ImageNet Scale with Differential Privacy
• Large Language Models Can Be Strong Differentially Private Learners
• DINOv3

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models