An algebraic approach to verifying galois-field arithmetic circuits with multiple-valued characteristics

Research output: Contribution to journalArticlepeer-review

Abstract

This study presents a formal verification method for Galois-field (GF) arithmetic circuits with the characteristics of more than two values. The proposed method formally verifies the correctness of circuit functionality (i.e., the input-output relations given as GF-polynomials) by checking the equivalence between a specification and a gate-level netlist. We represent a netlist using simultaneous algebraic equations and solve them based on a novel polynomial reduction method that can be efficiently applied to arithmetic over extension fields Fpm, where the characteristic p is larger than two. By using the reverse topological term order to derive the Gröbner basis, our method can complete the verification, even when a target circuit includes bugs. In addition, we introduce an extension of the Galois-Field binary moment diagrams to perform the polynomial reductions faster. Our experimental results show that the proposed method can efficiently verify practical Fpm arithmetic circuits, including those used in modern cryptography. Moreover, we demonstrate that the extended polynomial reduction technique can enable verification that is up to approximately five times faster than the original one.

Original languageEnglish
Pages (from-to)1083-1091
Number of pages9
JournalIEICE Transactions on Information and Systems
VolumeE104D
Issue number8
DOIs
Publication statusPublished - 2021

Keywords

  • Decision diagrams
  • Formal verification
  • Galois-field arithmetic circuits
  • Multiple-valued logic

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'An algebraic approach to verifying galois-field arithmetic circuits with multiple-valued characteristics'. Together they form a unique fingerprint.

Cite this