EzPC: Programmable, Efficient, and Scalable Secure Two-Party Computation for Machine Learning

Nishanth Chandran; Divya Gupta; Aseem Rastogi; Rahul Sharma; Shardul Tripathi

Paper 2017/1109

EzPC: Programmable, Efficient, and Scalable Secure Two-Party Computation for Machine Learning

Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma, and Shardul Tripathi

Abstract

We present EZPC: a secure two-party computation (2PC) framework that generates efficient 2PC protocols from high-level, easy-to-write, programs. EZPC provides formal correctness and security guarantees while maintaining performance and scalability. Previous language frameworks, such as CBMC-GC, ObliVM, SMCL, and Wysteria, generate protocols that use either arithmetic or boolean circuits exclusively. Our compiler is the first to generate protocols that combine both arithmetic sharing and garbled circuits for better performance. We empirically demonstrate that the protocols generated by our framework match or outperform (up to 19x) recent works that provide hand-crafted protocols for various functionalities such as secure prediction and matrix factorization.

Metadata

Available format(s): PDF
Category: Cryptographic protocols
Publication info: Preprint. MINOR revision.
Keywords: Secure Computation secure machine learning prediction
Contact author(s): divyagupta iitd @ gmail com
History: 2018-06-04: revised; 2017-11-20: received; See all versions
Short URL: https://ia.cr/2017/1109
License: CC BY

BibTeX

@misc{cryptoeprint:2017/1109,
      author = {Nishanth Chandran and Divya Gupta and Aseem Rastogi and Rahul Sharma and Shardul Tripathi},
      title = {{EzPC}: Programmable, Efficient, and Scalable Secure Two-Party Computation for Machine Learning},
      howpublished = {Cryptology {ePrint} Archive, Paper 2017/1109},
      year = {2017},
      url = {https://eprint.iacr.org/2017/1109}
}