Towards a certified proof checker for deep neural network verification

Desmartin, Remi, Isac, Omri, Passmore, Grant, Stark, Kathrin, Komendantskaya, Ekaterina and Katz, Guy (2023) Towards a certified proof checker for deep neural network verification. Glück, Robert and Kafle, Bishoksan (eds.) In Logic-Based Program Synthesis and Transformation - 33rd International Symposium, LOPSTR 2023, Proceedings. vol. 14330 LNCS, Springer Cham. pp. 198-209 . (doi:10.1007/978-3-031-45784-5_13).

Abstract

Recent developments in deep neural networks (DNNs) have led to their adoption in safety-critical systems, which in turn has heightened the need for guaranteeing their safety. These safety properties of DNNs can be proven using tools developed by the verification community. However, these tools are themselves prone to implementation bugs and numerical stability problems, which make their reliability questionable. To overcome this, some verifiers produce proofs of their results which can be checked by a trusted checker. In this work, we present a novel implementation of a proof checker for DNN verification. It improves on existing implementations by offering numerical stability and greater verifiability. To achieve this, we leverage two key capabilities of Imandra, an industrial theorem prover: its support for exact real arithmetic and its formal verification infrastructure. So far, we have implemented a proof checker in Imandra, specified its correctness properties and started to verify the checker’s compliance with them. Our ongoing work focuses on completing the formal verification of the checker and further optimising its performance.

This record has no associated files available for download.

Contributors

Author: Ekaterina Komendantskaya

Download statistics