Affiliation: School of Computing, Tokyo Institute of Technology
Computational Oblivious Transfer and Interactive Hashing
We present a simple approach for constructing oblivious transfer (OT) using a trapdoor function (TDF) and interactive hashing (IH). In a nutshell, an OT-receiver inputs a (randomly chosen) function index (encoded as a binary string) into IH. The resulting output strings are interpreted by an OT-sender and used to encrypt his private inputs. Two functions are shown to be eligible: 1) A specific candidate function: a coding based McEliece PKC; 2) A collection of TDF with some special properties, loosely speaking: succinctly representable index set and a unique trapdoor for each index. The aim of this presentation is to show a proof of concept in two ways: 1) Introduction of an apparent connection between OT and IH; 2) Emphasizing importance of IH as a cryptographic primitive in its own right and bringing up some aspects in which the further development of IH may be required.
Oblivious Transfer via McEliece's PKC and Permuted Kernels
We present two efficient protocols for two flavors of oblivious transfer (OT): the Rabin and 1-out-of-2 OT using the McEliece cryptosystem and Shamir's zero-knowledge identification scheme based on permuted kernels. This is a step towards diversifying computational assumptions on which OT -- the primitive of central importance -- can be based. Although we obtain a weak version of Rabin OT (where the malicious receiver may decrease his erasure probability), it can nevertheless be reduced to secure 1-out-of-2 OT. Elaborating on the first protocol, we provide a practical construction for 1-out-of-2 OT.