Paper 2022/866

Communication-Efficient Secure Logistic Regression

Amit Agarwal, University of Illinois Urbana-Champaign
Stanislav Peceny, Georgia Institute of Technology
Mariana Raykova, Google (United States)
Phillipp Schoppmann, Google (United States)
Karn Seth, Google (United States)

We present a new construction for secure logistic regression training, which enables two parties to train a model on private secret-shared data. Our goal is to minimize online communication and round complexity, while still allowing for an efficient offline phase. As part of our construction we develop many building blocks of independent interest. These include a new approximation technique for the sigmoid function, which results in a secure protocol with better communication; secure spline evaluation and secure powers computation protocols for fixed-point values; and a new comparison protocol that optimizes online communication. We also present a new two-party protocol for generating keys for distributed point functions (DPFs) over arithmetic sharing, where previous constructions do this only for Boolean outputs. We implement our protocol in an end-to-end system and benchmark its efficiency. We can securely evaluate a sigmoid in $18$ ms online time and $0.5$ KB of online communication. Our system can train a model over a database with $70,000$ samples and $15$ features with online communication of $208.09$ MB and online time of $2.24$ hours at the cost of $6.11$c over WAN. Our benchmarks demonstrate that we reduce online communication over state of the art by $\approx 10 \times$ for sigmoid and $\approx38\times$ for logistic regression training.

Available format(s)
Cryptographic protocols
Publication info
Secure Multiparty ComputationFunction Secret SharingLogistic RegressionSecure Comparison
Contact author(s)
amita2 @ illinois edu
stan peceny @ gatech edu
marianar @ google com
schoppmann @ google com
karn @ google com
2023-01-26: last of 2 revisions
2022-07-02: received
See all versions
Short URL
No rights reserved


      author = {Amit Agarwal and Stanislav Peceny and Mariana Raykova and Phillipp Schoppmann and Karn Seth},
      title = {Communication-Efficient Secure Logistic Regression},
      howpublished = {Cryptology ePrint Archive, Paper 2022/866},
      year = {2022},
      note = {\url{}},
      url = {}
Note: In order to protect the privacy of readers, does not use cookies or embedded third party content.