用李普希茨常数量化神经网络鲁棒性，指导安全机器人系统设计。
Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity
- 通过网络结构推导李普希茨常数公式，实现鲁棒性理论估算。
- 实验表明李普希茨常数与模型对小扰动的敏感度显著相关。
- 适合关注机器人感知系统安全性的研究者和工程师参考。
确保神经网络的鲁棒性对于机器人学习系统的安全可靠运行至关重要，尤其是在真实环境中的感知与决策任务中。本文研究感知系统中神经网络的鲁棒性，重点关注其对目标性、小规模扰动的敏感性。我们识别出李普希茨常数（Lipschitz constant）是量化和提升网络鲁棒性的关键指标。基于神经网络架构，推导出计算该常数的解析表达式，为鲁棒性评估与改进提供了理论基础。多个实验揭示了网络设计、李普希茨常数与鲁棒性之间的关系，为开发更安全、更鲁棒的机器人学习系统提供了实用洞见。
原文摘要 · Abstract (English)
Ensuring neural network robustness is essential for the safe and reliable operation of robotic learning systems, especially in perception and decision-making tasks within real-world environments. This paper investigates the robustness of neural networks in perception systems, specifically examining their sensitivity to targeted, small-scale perturbations. We identify the Lipschitz constant as a key metric for quantifying and enhancing network robustness. We derive an analytical expression to compute the Lipschitz constant based on neural network architecture, providing a theoretical basis for estimating and improving robustness. Several experiments reveal the relationship between network design, the Lipschitz constant, and robustness, offering practical insights for developing safer, more robust robot learning systems.
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。