Paper ID: 2207.06755

Verification of Sigmoidal Artificial Neural Networks using iSAT

Dominik Grundt, Sorin Liviu Jurj, Willem Hagemann, Paul Kröger, Martin Fränzle

This paper presents an approach for verifying the behaviour of nonlinear Artificial Neural Networks (ANNs) found in cyber-physical safety-critical systems. We implement a dedicated interval constraint propagator for the sigmoid function into the SMT solver iSAT and compare this approach with a compositional approach encoding the sigmoid function by basic arithmetic features available in iSAT and an approximating approach. Our experimental results show that the dedicated and the compositional approach clearly outperform the approximating approach. Throughout all our benchmarks, the dedicated approach showed an equal or better performance compared to the compositional approach.

Submitted: Jul 14, 2022