论文标题
fi-ode：在神经odes中证明稳健的前向不变性
FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs
论文作者
论文摘要
向前的不变性是控制理论中长期研究的属性，用于证明动态系统一直存在于某些预先指定的状态中，并且还承认稳健性保证（例如，证书在扰动下持有）。我们提出了一个培训的一般框架，并证明了神经odes中强大的前向不变性。我们将此框架应用于可靠的连续控制方面的认证安全性。据我们所知，这是培训这种非易变认证保证的培训神经ode政策的第一例。此外，我们通过使用该框架来探索框架的通用性来证明对抗性鲁棒性进行图像分类。
Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e.g., the certificate holds under perturbations). We propose a general framework for training and provably certifying robust forward invariance in Neural ODEs. We apply this framework to provide certified safety in robust continuous control. To our knowledge, this is the first instance of training Neural ODE policies with such non-vacuous certified guarantees. In addition, we explore the generality of our framework by using it to certify adversarial robustness for image classification.
