Answers are grounded in this paper and cite their sources.
In recent years, machine learning has been widely used in data analysis for predicting models, suchas face/pattern recognition, image processing, simultaneous interpretation and speech recognition.However, these massive data are sensitive, which raises privacy concerns. Therefore, to protect thedata privacy, in this paper, we design a scheme for securely training machine learning model on thejointed data that provided from different sources. Our scheme falls in the two-server-aided modeland allows one server to conduct most of computations, and another server to provides auxiliarycomputation. We prove the security of our scheme in the semi-honest model.
No takes yet. Share an insight, caveat, or question.
Li et al. (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: