sesa 18: e3

Research Article

Privacy Preserving Collaborative Machine Learning

Download17 downloads
  • @ARTICLE{10.4108/eai.14-7-2021.170295,
        author={Zheyuan Liu and Rui Zhang},
        title={Privacy Preserving Collaborative Machine Learning},
        journal={EAI Endorsed Transactions on Security and Safety: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={SESA},
        year={2021},
        month={7},
        keywords={Collaborative Machine Learning, Privacy Preservation, ADMM, Secure Aggregation, Security},
        doi={10.4108/eai.14-7-2021.170295}
    }
    
  • Zheyuan Liu
    Rui Zhang
    Year: 2021
    Privacy Preserving Collaborative Machine Learning
    SESA
    EAI
    DOI: 10.4108/eai.14-7-2021.170295
Zheyuan Liu1, Rui Zhang1,*
  • 1: University of Delaware, Newark, DE 19716
*Contact email: ruizhang@udel.edu

Abstract

Collaborative machine learning is a promising paradigm that allows multiple participants to jointly train a machine learning model without exposing their private datasets to other parties. Although collaborative machine learning is more privacy-friendly compared with conventional machine learning methods, the intermediate model parameters exchanged among different participants in the training process may still reveal sensitive information about participants’ local datasets. In this paper, we introduce a novel privacy-preserving collaborative machine learning mechanism by utilizing two non-colluding servers to perform secure aggregation of the intermediate parameters from participants. Compared with other existing solutions, our solution can achieve the same level of accuracy while incurring significantly lower computational cost.