# BoxRL-NNV: Boxed Refinement of Latin Hypercube Samples for Neural Network Verification

arXiv: https://arxiv.org/abs/2504.03650 · HTML: https://mlsanity.com/paper/2504.03650/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Marabou 2.0: A Versatile Formal Analyzer of Neural Networks](https://mlsanity.com/paper/2401.14461/) (2024)
- [Deep Neural Decision Trees](https://mlsanity.com/paper/1806.06988/) (2018)
- [The Fourth International Verification of Neural Networks Competition (VNN-COMP 2023): Summary and Results](https://mlsanity.com/paper/2312.16760/) (2023)
- [A DPLL(T) Framework for Verifying Deep Neural Networks](https://mlsanity.com/paper/2307.10266/) (2023)
- [Gaussian Process Surrogate Models for Neural Networks](https://mlsanity.com/paper/2208.06028/) (2022)

## Abstract (arXiv)

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).