Paper 2022/202

Through the Looking-Glass: Benchmarking Secure Multi-Party Computation Comparisons for ReLU's

Abdelrahaman Aly, Technology Innovation Institute
Kashif Nawaz, Technology Innovation Institute
Eugenio Salazar, Technology Innovation Institute
Victor Sucasas, Technology Innovation Institute
Abstract

Comparisons or Inequality Tests are an essential building block of Rectified Linear Unit functions (ReLU's), ever more present in Machine Learning, specifically in Neural Networks. Motivated by the increasing interest in privacy-preserving Artificial Intelligence, we explore the current state of the art of privacy preserving comparisons over Multi-Party Computation (MPC). We then introduce constant round variations and combinations, which are compatible with customary fixed point arithmetic over MPC. Our main focus is implementation and benchmarking; hence, we showcase our contributions via an open source library, compatible with current MPC software tools. Furthermore, we include a comprehensive comparative analysis on various adversarial settings. Our results improve running times in practical scenarios. Finally, we offer conclusions about the viability of these protocols when adopted for privacy-preserving Machine Learning.

Note: Less typos and grammar corrected. Camera Ready Version

Metadata
Available format(s)
PDF
Category
Applications
Publication info
Published elsewhere. CANS 2022
Keywords
Secure Multiparty Computation Privacy Preserving Machine Learning Applied Cryptography ReLU Functions
Contact author(s)
Abdelrahaman aly @ gmail com
Kashif nawaz @ tii ae
eugenio salazar @ tii ae
victor sucasas @ tii ae
History
2022-09-15: last of 5 revisions
2022-02-20: received
See all versions
Short URL
https://ia.cr/2022/202
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2022/202,
      author = {Abdelrahaman Aly and Kashif Nawaz and Eugenio Salazar and Victor Sucasas},
      title = {Through the Looking-Glass: Benchmarking Secure Multi-Party Computation Comparisons for {ReLU}'s},
      howpublished = {Cryptology {ePrint} Archive, Paper 2022/202},
      year = {2022},
      url = {https://eprint.iacr.org/2022/202}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.