Secure multiparty computations in floating-point arithmetic
This work addresses privacy concerns in distributed machine learning by enabling secure computations with minimal information leakage, though it is incremental as it builds on existing secure multiparty computation methods.
The paper tackles the problem of performing secure multiparty computations for privacy-preserving machine learning using standard floating-point arithmetic, achieving high performance on commodity hardware with rigorous proofs of worst-case bounds on information loss and numerical stability.
Secure multiparty computations enable the distribution of so-called shares of sensitive data to multiple parties such that the multiple parties can effectively process the data while being unable to glean much information about the data (at least not without collusion among all parties to put back together all the shares). Thus, the parties may conspire to send all their processed results to a trusted third party (perhaps the data provider) at the conclusion of the computations, with only the trusted third party being able to view the final results. Secure multiparty computations for privacy-preserving machine-learning turn out to be possible using solely standard floating-point arithmetic, at least with a carefully controlled leakage of information less than the loss of accuracy due to roundoff, all backed by rigorous mathematical proofs of worst-case bounds on information loss and numerical stability in finite-precision arithmetic. Numerical examples illustrate the high performance attained on commodity off-the-shelf hardware for generalized linear models, including ordinary linear least-squares regression, binary and multinomial logistic regression, probit regression, and Poisson regression.