AI RESEARCH
A Multiparty Homomorphic Encryption Approach to Confidential Federated Kaplan Meier Survival Analysis
arXiv CS.AI
•
ArXi:2412.20495v2 Announce Type: replace-cross The proliferation of real-world health data enables multi-institutional survival studies, yet privacy constraints preclude centralizing sensitive records. We present a privacy-preserving federated Kaplan--Meier framework based on threshold CKKS (Cheon-Kim-Kim-Song) homomorphic encryption that s approximate floating-point computation and encrypted aggregation of per-time-point counts while exposing only public outputs.