Paper ID: 2207.10562

CheckINN: Wide Range Neural Network Verification in Imandra (Extended)

Remi Desmartin, Grant Passmore, Ekaterina Komendantskaya, Matthew Daggitt

Neural networks are increasingly relied upon as components of complex safety-critical systems such as autonomous vehicles. There is high demand for tools and methods that embed neural network verification in a larger verification cycle. However, neural network verification is difficult due to a wide range of verification properties of interest, each typically only amenable to verification in specialised solvers. In this paper, we show how Imandra, a functional programming language and a theorem prover originally designed for verification, validation and simulation of financial infrastructure can offer a holistic infrastructure for neural network verification. We develop a novel library CheckINN that formalises neural networks in Imandra, and covers different important facets of neural network verification.

Submitted: Jul 21, 2022