End-to-End Verification for Subgraph Solving
Paper i proceeding, 2024

Modern subgraph-finding algorithm implementations consist of thousands of lines of highly optimized code, and this complexity raises questions about their trustworthiness. Recently, some state-of-the-art subgraph solvers have been enhanced to output machine-verifiable proofs that their results are correct. While this significantly improves reliability, it is not a fully satisfactory solution, since end-users have to trust both the proof checking algorithms and the translation of the high-level graph problem into a low-level 0-1 integer linear program (ILP) used for the proofs. In this work, we present the first formally verified toolchain capable of full end-to-end verification for subgraph solving, which closes both of these trust gaps. We have built encoder frontends for various graph problems together with a 0-1 ILP (a.k.a. pseudo-Boolean) proof checker, all implemented and formally verified in the CAKEML ecosystem. This toolchain is flexible and extensible, and we use it to build verified proof checkers for both decision and optimization graph problems, namely, subgraph isomorphism, maximum clique, and maximum common (connected) induced subgraph. Our experimental evaluation shows that end-to-end formal verification is now feasible for a wide range of hard graph problems.

Författare

Stephan Gocht

Lunds universitet

Köpenhamns universitet

Ciaran McCreesh

University of Glasgow

Magnus Myreen

Göteborgs universitet

Chalmers, Data- och informationsteknik, Formella metoder

Jakob Nordström

Lunds universitet

Köpenhamns universitet

Andy Oertel

Köpenhamns universitet

Lunds universitet

Yong Kiam Tan

Agency for Science, Technology and Research (A*STAR)

Proceedings of the AAAI Conference on Artificial Intelligence

21595399 (ISSN) 23743468 (eISSN)

Vol. 38 8 8038-8047

38th AAAI Conference on Artificial Intelligence, AAAI 2024
Vancouver, Canada,

Ämneskategorier

Datavetenskap (datalogi)

Datorsystem

DOI

10.1609/aaai.v38i8.28642

Mer information

Senast uppdaterat

2024-09-26