Key points are not available for this paper at this time.
Homomorphic encryption (HE) schemes, such as the Cheon-Kim-Kim-Song (CKKS) algorithm, offer immense potential for secure computation on encrypted data, particularly within privacy-sensitive domains like machine learning. However, the computational overhead inherent in CKKS operations often poses challenges, particularly for processing large-scale datasets and complex computations. In this paper, we present a new approach to mitigate these challenges by integrating innovative data compression techniques, resulting in a staggering 90% reduction in data size. Coupled with harnessing the computational prowess of graphics processing units (GPUs), our experimental results showcase remarkable achievements, with processing times reduced by up to 100 times compared to traditional methods. Our method ensures data confidentiality while addressing performance bottlenecks in CKKS-based computations, paving the way for efficient and scalable HE applications.
Phan et al. (Tue,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: