An Extention of Lazy Abstraction and Refinement for Program Verification

Abstract

Predicate abstraction techniques have been shown to be a powerful technique for verifying imperative programs, which can solve the problem of state space explosion pretty well. Among them, lazy abstraction with interpolation-based refinement also called the IMPACT approach has gained increasing popularity in the last years. However, despite its high efficiency, the IMPACT fails to work out some kinds of the programs because the interpolants produced by interpolant solver are so bad to make the verification divergent. According to the features of some of these programs, we extend the IMPACT method to make it applicable for them. In addition to its basic ones, two other operations are introduced to the IMPACT refinement to guide it produce reasonal interpolants which are helpful for the verification process to converge. The experiments on the benchmark of SV-COMP2020 show the potential of the extended approach.