Abstract
When two or more parties need to compute a common result while safeguarding their sensitive inputs, they use secure multiparty computation (SMC) techniques such as garbled circuits. The traditional enabler of SMC is cryptography, but the significant number of cryptographic operations required results in these techniques being impractical for most real-time, online computations. Trusted execution environments (TEEs) provide hardware-enforced isolation of code and data in use, making them promising candidates for making SMC more tractable. This paper revisits the history of improvements to SMC over the years and considers the possibility of coupling trusted hardware with SMC. This paper also addresses three open challenges: (1) defeating malicious adversaries, (2) mobile-friendly TEE-supported SMC, and (3) a more general coupling of trusted hardware and privacy-preserving computation.
Highlights
Secure multiparty computation (SMC) allows two or more parties to collectively perform some computation and receive the resulting output without ever exposing any party’s sensitive input
Following its beginnings in the 1980s with Yao’s work on two-party garbled circuit computation [1, 2], SMC techniques have rapidly improved in the past several decades, with costs lowered by orders of magnitude
Secure multiparty computation cannot yet be considered sufficiently practical for use in a majority of applications where real-time performance is required. (It is certainly possible to support some subset of applications with the current iteration of SMC, but SMC in real-time environmental constraints is not yet a widespread phenomenon.) This is especially true for techniques based on fully homomorphic encryption [5] or secret sharing [6, 7]. (Depending on the application, secret sharing may be preferable to GC, such as for matrix and tensor operations or operations that follow the mapreduce paradigm.) Partial homomorphic encryption, while offering better performance than its fully homomorphic counterpart, is limited in the operations it can support
Summary
Secure multiparty computation (SMC) allows two or more parties to collectively perform some computation and receive the resulting output without ever exposing any party’s sensitive input. Recent work [3] demonstrates garbled circuit evaluation at speeds of 1.15 billion gates/second, and secret sharing supported privacy-preserving location services were available at Real World Crypto 2015 [4] Despite these significant gains, secure multiparty computation cannot yet be considered sufficiently practical for use in a majority of applications where (near) real-time performance is required. (Depending on the application, secret sharing may be preferable to GC, such as for matrix and tensor operations or operations that follow the mapreduce paradigm.) Partial homomorphic encryption, while offering better performance than its fully homomorphic counterpart, is limited in the operations it can support All these techniques share a common limitation, this being the substantial amount of cryptographic operations that are required of the parties involved, even in the two-party setting, or the requirement for a secure communication channel. The remainder of the paper is organized as follows: Section 2 describes the fundamentals of and explores recent advances in secure multiparty computation; Section 3 considers grounding of trust in hardware and presents a number of security solutions that already make use of trusted hardware; Section 4 addresses several open challenges surrounding hardware-assisted secure computation and proposes steps forward for each; and Section 5 concludes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
