CANAL: חברותה של רעש תגובה-ערות להפרדה-פרטית של תיאורי-מאפיינים בתחום ההסגמנטציה של תמונות-רפואיות

תקציר מקורי באנגליתarXiv:2609.13271v1 Announce Type: cross Abstract: 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 iteration, so each patient image is released many times and the privacy cost composes over those releases, growing by orders of magnitude. We present a sample