A Certified Proof Checker for Deep Neural Network Verification in Imandra

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Desmartin, Remi, Isac, Omri, Passmore, Grant, Komendantskaya, Ekaterina, Stark, Kathrin, Katz, Guy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915356724953088
author Desmartin, Remi
Isac, Omri
Passmore, Grant
Komendantskaya, Ekaterina
Stark, Kathrin
Katz, Guy
author_facet Desmartin, Remi
Isac, Omri
Passmore, Grant
Komendantskaya, Ekaterina
Stark, Kathrin
Katz, Guy
contents Recent advances in the verification of deep neural networks (DNNs) have opened the way for a broader usage of DNN verification technology in many application areas, including safety-critical ones. However, DNN verifiers are themselves complex programs that have been shown to be susceptible to errors and numerical imprecision; this, in turn, has raised the question of trust in DNN verifiers. One prominent attempt to address this issue is enhancing DNN verifiers with the capability of producing certificates of their results that are subject to independent algorithmic checking. While formulations of Marabou certificate checking already exist on top of the state-of-the-art DNN verifier Marabou, they are implemented in C++, and that code itself raises the question of trust (e.g., in the precision of floating point calculations or guarantees for implementation soundness). Here, we present an alternative implementation of the Marabou certificate checking in Imandra -- an industrial functional programming language and an interactive theorem prover (ITP) -- that allows us to obtain full proof of certificate correctness. The significance of the result is two-fold. Firstly, it gives stronger independent guarantees for Marabou proofs. Secondly, it opens the way for the wider adoption of DNN verifiers in interactive theorem proving in the same way as many ITPs already incorporate SMT solvers.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10611
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Certified Proof Checker for Deep Neural Network Verification in Imandra
Desmartin, Remi
Isac, Omri
Passmore, Grant
Komendantskaya, Ekaterina
Stark, Kathrin
Katz, Guy
Logic in Computer Science
Artificial Intelligence
Programming Languages
Recent advances in the verification of deep neural networks (DNNs) have opened the way for a broader usage of DNN verification technology in many application areas, including safety-critical ones. However, DNN verifiers are themselves complex programs that have been shown to be susceptible to errors and numerical imprecision; this, in turn, has raised the question of trust in DNN verifiers. One prominent attempt to address this issue is enhancing DNN verifiers with the capability of producing certificates of their results that are subject to independent algorithmic checking. While formulations of Marabou certificate checking already exist on top of the state-of-the-art DNN verifier Marabou, they are implemented in C++, and that code itself raises the question of trust (e.g., in the precision of floating point calculations or guarantees for implementation soundness). Here, we present an alternative implementation of the Marabou certificate checking in Imandra -- an industrial functional programming language and an interactive theorem prover (ITP) -- that allows us to obtain full proof of certificate correctness. The significance of the result is two-fold. Firstly, it gives stronger independent guarantees for Marabou proofs. Secondly, it opens the way for the wider adoption of DNN verifiers in interactive theorem proving in the same way as many ITPs already incorporate SMT solvers.
title A Certified Proof Checker for Deep Neural Network Verification in Imandra
topic Logic in Computer Science
Artificial Intelligence
Programming Languages
url https://arxiv.org/abs/2405.10611