Revisiting PGD Attacks for Stability Analysis of High-Dimensional Nonlinear Systems and Perception-Based Control-Reference-Cited by-同舟云学术

Revisiting PGD Attacks for Stability Analysis of High-Dimensional Nonlinear Systems and Perception-Based Control

Published:2023 Issue: Volume:7 Page:343-348
ISSN:2475-1456
Container-title:IEEE Control Systems Letters
language:
Short-container-title:IEEE Control Syst. Lett.

Author:

Havens Aaron¹^ORCID,Kevian Darioush²,Seiler Peter³^ORCID,Dullerud Geir²^ORCID,Hu Bin¹^ORCID

Affiliation:

1. Coordinated Science Laboratory and the Department of Electrical and Computer Engineering, University of Illinois at Urbana–Champaign, Champaign, IL, USA

2. Coordinated Science Laboratory and the Department of Mechanical Science and Engineering, University of Illinois at Urbana, Champaign, IL, USA

3. Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA

Funder

NSF Award CAREER

2020 Amazon Research Award

NSF

U.S. Office of Naval Research

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Control and Optimization,Control and Systems Engineering

Link

https://ieeexplore.ieee.org/ielam/7782633/9828546/9814867-aam.pdf

Reference36 articles.

1. On the stability and convergence of robust adversarial reinforcement learning: A case study on linear quadratic systems;zhang;Proc Adv Neural Inf Process Syst,2020

2. H? model-free reinforcement learning with robust stability guarantee;han;arXiv 1911 02875,2019

3. Policy optimization for H2 linear control with H? robustness guarantee: Implicit Regularization and global convergence;zhang;Proc Learn Dyn Control,2020

4. Soft actor–critic algorithms and applications;haarnoja;arXiv 1812 05905,2018

5. Model-free ? synthesis via adversarial reinforcement learning;keivan;arXiv 2111 15537,2021

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Building a Robust and Efficient Defensive System Using Hybrid Adversarial Attack;IEEE Transactions on Artificial Intelligence;2024-09

2. Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control;2022 IEEE 61st Conference on Decision and Control (CDC);2022-12-06