BoxRL-NNV: Boxed Refinement of Latin Hypercube Samples for Neural Network Verification
This addresses safety verification for neural networks, but appears incremental as it builds on existing sampling and optimization methods.
The paper tackles the problem of detecting safety violations in neural networks by computing output bounds from input bounds, using Latin Hypercube Sampling and L-BFGS-B refinement, with results reported for a subset of the ACAS Xu benchmark.
BoxRL-NNV 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 Latin Hypercube Sampling, and further refinement using L-BFGS-B for local optimization around the initial guess. This paper presents an overview of BoxRL-NNV, as well as our results for a subset of the ACAS Xu benchmark. A complete evaluation of the tool's performance, including benchmark comparisons with state-of-the-art tools, shall be presented at the Sixth International Verification of Neural Networks Competition (VNN-COMP'25).