Real-time out-of-distribution detection in cyber-physical systems with learning-enabled components

IF 1.7 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS
Feiyang Cai, Xenofon Koutsoukos
{"title":"Real-time out-of-distribution detection in cyber-physical systems with learning-enabled components","authors":"Feiyang Cai,&nbsp;Xenofon Koutsoukos","doi":"10.1049/cps2.12034","DOIUrl":null,"url":null,"abstract":"<p>Learning-enabled components (LECs) such as deep neural networks are used increasingly in cyber-physical systems (CPS) since they can handle the uncertainty and variability of the environment and increase the level of autonomy. LECs, however, may compromise system safety since their predictions may have large errors, for example, when the data available at runtime are different than the data used for training. This study considers the problem of efficient and robust out-of-distribution detection for learning-enabled CPS. Out-of-distribution detection using a single input example is typically not robust and may result in a large number of false alarms. The proposed approach utilises neural network architectures that are used to compute efficiently the nonconformity of new inputs relative to the training data. Specifically, variational autoencoder and deep support vector data description networks are used to learn models for the real-time detection of out-of-distribution high-dimensional inputs. Robustness can be improved by incorporating saliency maps that identify parts of the input contributing most to the LEC predictions. We demonstrate the approach using simulation case studies of an advanced emergency braking system and a self-driving end-to-end controller, as well as a real-world data set for autonomous driving. The experimental results show a small detection delay with a very small number of false alarms while the execution time is comparable to the execution time of the original LECs.</p>","PeriodicalId":36881,"journal":{"name":"IET Cyber-Physical Systems: Theory and Applications","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2022-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cps2.12034","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Cyber-Physical Systems: Theory and Applications","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cps2.12034","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Learning-enabled components (LECs) such as deep neural networks are used increasingly in cyber-physical systems (CPS) since they can handle the uncertainty and variability of the environment and increase the level of autonomy. LECs, however, may compromise system safety since their predictions may have large errors, for example, when the data available at runtime are different than the data used for training. This study considers the problem of efficient and robust out-of-distribution detection for learning-enabled CPS. Out-of-distribution detection using a single input example is typically not robust and may result in a large number of false alarms. The proposed approach utilises neural network architectures that are used to compute efficiently the nonconformity of new inputs relative to the training data. Specifically, variational autoencoder and deep support vector data description networks are used to learn models for the real-time detection of out-of-distribution high-dimensional inputs. Robustness can be improved by incorporating saliency maps that identify parts of the input contributing most to the LEC predictions. We demonstrate the approach using simulation case studies of an advanced emergency braking system and a self-driving end-to-end controller, as well as a real-world data set for autonomous driving. The experimental results show a small detection delay with a very small number of false alarms while the execution time is comparable to the execution time of the original LECs.

Abstract Image

具有学习功能组件的网络物理系统中的实时分布外检测
学习支持组件(LECs),如深度神经网络,越来越多地用于网络物理系统(CPS),因为它们可以处理环境的不确定性和可变性,并提高自治水平。然而,LECs可能会危及系统安全性,因为它们的预测可能有很大的错误,例如,当运行时可用的数据与用于训练的数据不同时。本文研究了基于学习的CPS的高效鲁棒的分布外检测问题。使用单个输入示例的分布外检测通常不具有鲁棒性,并且可能导致大量的假警报。提出的方法利用神经网络架构,用于有效地计算相对于训练数据的新输入的不一致性。具体来说,采用变分自编码器和深度支持向量数据描述网络来学习模型,用于实时检测分布外的高维输入。鲁棒性可以通过结合识别对LEC预测贡献最大的输入部分的显著性图来提高。我们使用先进的紧急制动系统和自动驾驶端到端控制器的仿真案例研究以及自动驾驶的真实数据集来演示该方法。实验结果表明,该方法的检测延迟小,虚警数量极少,执行时间与原lec的执行时间相当。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IET Cyber-Physical Systems: Theory and Applications
IET Cyber-Physical Systems: Theory and Applications Computer Science-Computer Networks and Communications
CiteScore
5.40
自引率
6.70%
发文量
17
审稿时长
19 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信