SecureMed: Secure Medical Computation Using GPU-Accelerated Homomorphic Encryption Scheme

Alhassan Khedr, Glenn Gulak
2018 IEEE journal of biomedical and health informatics  
Sharing the medical records of individuals among healthcare providers and researchers around the world can accelerate advances in medical research. While the idea seems increasingly practical due to cloud data services, maintaining patient privacy is of paramount importance. Standard encryption algorithms help protect sensitive data from outside attackers but they cannot be used to compute on this sensitive data while being encrypted. Homomorphic Encryption (HE) presents a very useful tool that
more » ... can compute on encrypted data without the need to decrypt it. In this work, we describe an optimized NTRUbased implementation of the GSW homomorphic encryption scheme. Our results show a factor of 58× improvement in CPU performance compared to other recent work on encrypted medical data under the same security settings. Our system is built to be easily portable to GPUs resulting in an additional speedup of up to a factor of 104× (and 410×) to offer an overall speedup of 6085× (and 24011×) using a single GPU (or four GPUs), respectively.
doi:10.1109/jbhi.2017.2657458 pmid:28129194 fatcat:n54mkvbn2bbebiz2qkekbrsbte