SobolBox: Boxed Refinement of Sobol Sequence Samples for Neural Network Verification (Competition Contribution)

SobolBox is a Python tool for the detection of safety violations in neural networks by computing the bounds of the output variables, given the bounds of the input variables of the network. This is done using global extrema estimation via Sobol sequence sampling, and further refinement using L-BFGS-B for local optimization around the initial guess. This paper presents an overview of SobolBox, as well as our results for the ACAS Xu benchmarks.