Corpus ID: 57373856

Secure Computation for Machine Learning With SPDZ

@article{Chen2019SecureCF,
  title={Secure Computation for Machine Learning With SPDZ},
  author={V. Chen and Valerio Pastro and Mariana Raykova},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.00329}
}
  • V. Chen, Valerio Pastro, Mariana Raykova
  • Published 2019
  • Computer Science
  • ArXiv
  • Secure Multi-Party Computation (MPC) is an area of cryptography that enables computation on sensitive data from multiple sources while maintaining privacy guarantees. However, theoretical MPC protocols often do not scale efficiently to real-world data. This project investigates the efficiency of the SPDZ framework, which provides an implementation of an MPC protocol with malicious security, in the context of popular machine learning (ML) algorithms. In particular, we chose applications such as… CONTINUE READING
    25 Citations
    A Scalable Approach for Privacy-Preserving Collaborative Machine Learning
    • PDF
    MPC-enabled Privacy-Preserving Neural Network Training against Malicious Attack
    • PDF
    Secure Byzantine-Robust Machine Learning
    • 6
    • PDF
    Accelerating 2PC-based ML with Limited Trusted Hardware
    • 1
    • Highly Influenced
    • PDF
    Revisiting Secure Computation Using Functional Encryption: Opportunities and Research Directions
    • PDF
    Privacy-Preserving Deep Learning with SPDZ
    • 1
    • PDF
    CrypTFlow2: Practical 2-Party Secure Inference
    • 1
    • PDF

    References

    SHOWING 1-10 OF 10 REFERENCES
    Privacy-Preserving Distributed Linear Regression on High-Dimensional Data
    • 92
    • PDF
    SecureML: A System for Scalable Privacy-Preserving Machine Learning
    • 590
    • Highly Influential
    • PDF
    Multiparty Computation from Somewhat Homomorphic Encryption
    • 736
    • PDF
    A Note on the Relation between the Definitions of Security for Semi-Honest and Malicious Adversaries
    • 10
    • PDF
    An architecture for practical actively secure MPC with dishonest majority
    • 81
    • PDF
    Overdrive: Making SPDZ Great Again
    • 103
    • PDF
    Obliv-C: A Language for Extensible Data-Oblivious Computation
    • 121
    • PDF
    The Basic Applications
    • 42
    The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition
    • 13,456
    • PDF
    The Foundations of Cryptography - Volume 2: Basic Applications
    • 1,077
    • Highly Influential
    • PDF