Tutorial: Neural Network and Autonomous Cyber-Physical Systems Formal Verification for Trustworthy AI and Safe Autonomy

Tutorial: Neural Network and Autonomous Cyber-Physical Systems Formal Verification for Trustworthy AI and Safe Autonomy
复制标题

教程:神经网络和自主网络物理系统形式验证可信赖的人工智能和安全自治

DOI:
10.1145/3607890.3608454
复制
发表时间:
2023
期刊:
Proceedings of the International Conference on Embedded Software (EMSOFT '23
影响因子:
--
通讯作者:
Johnson, Taylor
Johnson, Taylor
中科院分区:
--
文献类型:
--
作者:
Tran, Hoang-Dung;Manzanas Lopez, Diego;Johnson, Taylor

文献摘要

参考文献

相似文献

本交互式教程描述了正式验证神经网络及其在安全关键网络物理系统(CPS)中的使用的最先进的方法。在安全关键应用中包含深度学习模型需要正式分析系统的行为,包括对单个组件的推理(例如,控制器鲁棒性),以及它们在整个系统中的相互作用和影响。本教程从一个关于这个新兴研究领域的讲座开始,然后是在软件工具中实现这些方法的演示,特别是神经网络验证(NNV)工具。例子包括航空航天、汽车等领域的系统。
This interactive tutorial describes state-of-the-art methods for formally verifying neural networks and their usage within safety-critical cyber-physical systems (CPS). The inclusion of deep learning models in safety-critical applications requires to formally analyze the behavior of the system, including reasoning about the individual components (e.g., controller robustness), and their interactions and effects in the system as a whole. This tutorial begins with a lecture on this emerging research area, followed by demos of these methods implemented in software tools, specifically the Neural Network Verification (NNV) tool. Examples include systems from aerospace, automotive, and beyond.
DOI: 10.1109/formalise58978.2023.00009
发表时间: 2023-05
期刊: 2023 IEEE/ACM 11th International Conference on Formal Methods in Software Engineering (FormaliSE)
影响因子: --
作者:
M. Ivashchenko;Sung-Woo Choi;L. V. Nguyen;Hoang-Dung Tran
通讯作者: M. Ivashchenko;Sung-Woo Choi;L. V. Nguyen;Hoang-Dung Tran
DOI: 10.2514/1.d0255
发表时间: 2022-10
影响因子: --
作者:
Diego Manzanas Lopez;Taylor T. Johnson;Stanley Bak;Hoang-Dung Tran;Kerianne L. Hobbs
通讯作者: Diego Manzanas Lopez;Taylor T. Johnson;Stanley Bak;Hoang-Dung Tran;Kerianne L. Hobbs
案例研究:无人水下航行器的安全验证
DOI: 10.1109/spw50608.2020.00047
发表时间: 2020
期刊: 2020 IEEE Security and Privacy Workshops (SPW)
影响因子: --
作者:
Diego Manzanas Lopez;Patrick Musau;Nathaniel P. Hamilton;Hoang;Taylor T. Jonhson
通讯作者: Taylor T. Jonhson
DOI: 10.1007/s10009-023-00703-4
发表时间: 2023-01
影响因子: 1.5
作者:
Christopher Brix;Mark Niklas Muller;Stanley Bak;Taylor T. Johnson;Changliu Liu
通讯作者: Christopher Brix;Mark Niklas Muller;Stanley Bak;Taylor T. Johnson;Changliu Liu
基于机器学习的网络物理系统的验证:比较研究
DOI: 10.1145/3501710.3519540
发表时间: 2022
期刊: Proceedings of the 25th ACM International Conference on Hybrid Systems: Computation and Control
影响因子: --
作者:
Arthur Clavière;Laura Altieri Sambartolomé;E. Asselin;C. Garion;C. Pagetti
通讯作者: C. Pagetti