arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.00801math.OCcs.LG
收藏

PGD攻击在大规模非线性系统稳定性分析和基于感知的控制中的应用

Revisiting PGD Attacks for Stability Analysis of Large-Scale Nonlinear Systems and Perception-Based Control

Aaron Havens, Darioush Keivan, Peter Seiler, Geir Dullerud, Bin Hu

摘要:

许多现有的区域吸引力(ROA)分析工具难以解决反馈系统与大规模神经网络(NN)的政策和/或高维传感模式,如相机。在本文中,我们定制了对抗学习社区中开发的投影梯度下降(PGD)攻击方法,作为大规模非线性系统和端到端感知控制的通用ROA分析工具。我们表明,ROA分析可以近似为一个约束最大化问题,其目标是找到最坏情况下的初始条件,转移的终态最。然后,我们提出了两个基于PGD的迭代法,可以用来解决由此产生的约束最大化问题。我们的分析不是基于李雅普诺夫理论,因此需要最少的信息的问题结构。在基于模型的设置,我们表明,PGD更新可以有效地使用反向传播。在无模型设置(这是更相关的ROA分析的感知控制),我们提出了一个有限差分PGD估计,这是一般的,只需要一个黑盒模拟器生成的轨迹的闭环系统给定的任何初态。我们展示了我们的分析工具的可扩展性和通用性的几个数值例子与大规模的NN政策和高维图像观测。我们相信,我们提出的分析作为一个有意义的第一步,进一步了解大规模非线性系统的闭环稳定性和基于感知的控制。

英文摘要:

Many existing region-of-attraction (ROA) analysis tools find difficulty in addressing feedback systems with large-scale neural network (NN) policies and/or high-dimensional sensing modalities such as cameras. In this paper, we tailor the projected gradient descent (PGD) attack method developed in the adversarial learning community as a general-purpose ROA analysis tool for large-scale nonlinear systems and end-to-end perception-based control. We show that the ROA analysis can be approximated as a constrained maximization problem whose goal is to find the worst-case initial condition which shifts the terminal state the most. Then we present two PGD-based iterative methods which can be used to solve the resultant constrained maximization problem. Our analysis is not based on Lyapunov theory, and hence requires minimum information of the problem structures. In the model-based setting, we show that the PGD updates can be efficiently performed using back-propagation. In the model-free setting (which is more relevant to ROA analysis of perception-based control), we propose a finite-difference PGD estimate which is general and only requires a black-box simulator for generating the trajectories of the closed-loop system given any initial state. We demonstrate the scalability and generality of our analysis tool on several numerical examples with large-scale NN policies and high-dimensional image observations. We believe that our proposed analysis serves as a meaningful initial step toward further understanding of closed-loop stability of large-scale nonlinear systems and perception-based control.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑