New distinguishers based on random mappings against stream ciphers

Abstract

Statistical randomness testing plays an important role in security analysis of cryptosystems. In this study, we aim to propose a new framework of randomness testing based on random mappings. Considering the probability distributions of coverage and P-lengths, we present three new distinguishers; (i) coverage test, (ii) p-test and (iii) DP-coverage test and applied them on Phase III Candidates of eSTREAM project. We experimentally observed some statistical weaknesses of Po-maranch using the coverage test.