Corpus ID: 59599882

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

@article{So2019CodedPrivateMLAF,
  title={CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning},
  author={Jinhyun So and Basak Guler and A. S. Avestimehr and Payman Mohassel},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.00641}
}
  • Jinhyun So, Basak Guler, +1 author Payman Mohassel
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • How to train a machine learning model while keeping the data private and secure. [...] Key Result Furthermore, via experiments over Amazon EC2, we demonstrate that CodedPrivateML can provide an order of magnitude speedup (up to $\sim 34\times$) over the state-of-the-art cryptographic approaches.Expand Abstract
    37 Citations

    Figures, Tables, and Topics from this paper

    A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
    • 1
    • PDF
    FLASH: Fast and Robust Framework for Privacy-preserving Machine Learning
    • 10
    • PDF
    Privacy-Preserving Distributed Learning in the Analog Domain
    • 3
    • PDF
    Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy
    • 121
    • PDF
    Privacy-Aware Distributed Graph-Based Semi-Supervised Learning
    Minimizing Latency for Secure Coded Computing Using Secret Sharing via Staircase Codes
    • 17
    • PDF
    Distributed Differentially Private Computation of Functions with Correlated Noise
    • 4
    • PDF

    References

    SHOWING 1-10 OF 35 REFERENCES
    SecureML: A System for Scalable Privacy-Preserving Machine Learning
    • 621
    • PDF
    ABY3: A Mixed Protocol Framework for Machine Learning
    • 171
    • PDF
    Privacy-Preserving Distributed Linear Regression on High-Dimensional Data
    • 95
    • PDF
    ML Confidential: Machine Learning on Encrypted Data
    • 323
    • PDF
    Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy
    • 121
    • PDF
    Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization
    • 51
    • PDF
    Privacy-Preserving Collaborative Model Learning: The Case of Word Vector Training
    • 27
    Privacy-preserving logistic regression
    • 442
    • PDF
    Exploiting Unintended Feature Leakage in Collaborative Learning
    • 256
    • PDF