Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.14123 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913126423724032 |
|---|---|
| author | Lee, Haebom Kim, Gyeongjung |
| author_facet | Lee, Haebom Kim, Gyeongjung |
| contents | Feature sharing via split inference offers a lightweight alternative to federated learning for resource-constrained hospitals, but transmitted features still leak patient identity information and lack practical mechanisms for controlled feature sharing. We propose Keyed Nonlinear Transform (KNT), a drop-in feature transformation that applies key-conditioned obfuscation to intermediate representations. KNT reduces re-identification AUC from 0.635 to 0.586, corresponding to a 36% reduction in above-chance identity signal, while introducing only 0.15 ms CPU overhead, without backbone retraining, and preserving classification performance within 1.0 pp. Our analysis shows that KNT's nonlinear transform prevents closed-form inversion and shifts recovery to iterative gradient-based optimization under full key compromise, substantially increasing inversion difficulty. The same transform generalizes to dense prediction tasks, incurring only a 4.4 pp Dice reduction on skin-lesion segmentation without retraining. These results position KNT as a practical and efficient privacy layer for split inference deployments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14123 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis Lee, Haebom Kim, Gyeongjung Image and Video Processing Computer Vision and Pattern Recognition Feature sharing via split inference offers a lightweight alternative to federated learning for resource-constrained hospitals, but transmitted features still leak patient identity information and lack practical mechanisms for controlled feature sharing. We propose Keyed Nonlinear Transform (KNT), a drop-in feature transformation that applies key-conditioned obfuscation to intermediate representations. KNT reduces re-identification AUC from 0.635 to 0.586, corresponding to a 36% reduction in above-chance identity signal, while introducing only 0.15 ms CPU overhead, without backbone retraining, and preserving classification performance within 1.0 pp. Our analysis shows that KNT's nonlinear transform prevents closed-form inversion and shifts recovery to iterative gradient-based optimization under full key compromise, substantially increasing inversion difficulty. The same transform generalizes to dense prediction tasks, incurring only a 4.4 pp Dice reduction on skin-lesion segmentation without retraining. These results position KNT as a practical and efficient privacy layer for split inference deployments. |
| title | Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14123 |