Secure multi-party linear regression at plaintext speed
This addresses the need for privacy-preserving data analysis in collaborative biomedical research, though it appears incremental as it builds on existing geometric ideas.
The paper tackled the problem of performing secure multi-party linear regression and feature selection efficiently, achieving speeds comparable to plaintext regression. This enables practical secure genome-wide association studies across multiple biobanks.
We detail distributed algorithms for scalable, secure multiparty linear regression and feature selection at essentially the same speed as plaintext regression. While the core geometric ideas are simple, the recognition of their broad utility when combined is novel. Our scheme opens the door to efficient and secure genome-wide association studies across multiple biobanks.