用采样与优化结合的方法，快速验证神经网络安全性
BoxRL-NNV: Boxed Refinement of Latin Hypercube Samples for Neural Network Verification
- 基于拉丁超立方采样初探输出边界，再用L-BFGS-B局部优化
- 在ACAS Xu部分测试中成功发现安全违规，结果可靠
- 适合关注神经网络验证的工程师和研究者使用
BoxRL-NNV 是一个用于检测神经网络安全违规的 Python 工具，通过给定输入变量的边界来计算输出变量的边界。该方法采用拉丁超立方采样进行全局极值估计，并利用 L-BFGS-B 在初始猜测附近进行局部优化以进一步细化结果。本文介绍了 BoxRL-NNV 的整体架构，并展示了其在 ACAS Xu 基准测试子集上的验证结果。工具完整性能评估，包括与当前先进工具的对比，将在第六届国际神经网络验证竞赛（VNN-COMP'25）上发布。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。