Development of Privacy-preserving Deep Learning Model with Homomorphic Encryption: A Technical Feasibility Study in Kidney CT Imaging

Sangwook Lee, Jong‐Min Choi, Min-Je Park, Hajin Kim, Soo‐Heang Eo, Garam Lee, Sulgi Kim, Jungyo Suh · Radiology Artificial Intelligence · 2025

Homomorphic encryption can be integrated into deep learning models for CT-based kidney mass classification, achieving diagnostic performance similar to that of nonencrypted models while ensuring privacy protection, although with increased storage and processing time demands.

Read the paper · More papers on PaperTik