EzPC: Programmable and efficient secure two-party computation for machine learning

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 and boolean circuits for better performance. We empirically demonstrate that the performance of the protocols generated by EzPC is comparable to or better than (in some cases upto 19x) their state-of-the-art, hand-crafted implementations, while EzPC protocols also outperform their boolean circuits only counterparts by as much as 25x.