SOURCE-LINKED INTELLIGENCE

CANAL: Channel-Aware Noise Allocation for Differentially Private Feature Distillation in Medical Image Segmentation

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Medical image segmentation needs diverse training data, but hospitals hold complementary scans they cannot share for privacy and regulatory reasons. Knowledge distillation can bridge this gap by exporting learned feature representations instead of images, but those representations still encode patient-specific anatomy and remain vulnerable to membership-inference and feature-inversion attacks. Adding calibrated Gaussian noise restores a differential-privacy guarantee, yet three issues have been overlooked. First, prior DP feature-distillation pipelines re-sample noise at every student iteratio

Read original source ↗ Open in workspace

recordType

paper

region

Global