Reinforcement Learning-Based Detection for State Estimation Under False Data Injection

We consider the problem of network security under false data injection attacks over wireless sensor networks.To resist the attacks which can inject false data into communication channels according to a certain probability, we formulate the online attack detection problem as a partially observable Ma...

Full description

Bibliographic Details
Main Authors:	Weiliang Jiang, Wen Yang, Jiayu Zhou, Wenjie Ding, Yue Luo, Yun Liu
Format:	Article
Language:	English
Published:	IEEE 2021-01-01
Series:	IEEE Access
Subjects:	Wireless sensor network false data injection attack reinforcement learning partially observable Markov decision process
Online Access:	https://ieeexplore.ieee.org/document/9419373/

id	doaj-367e267342994d21bf78c3183f380d63
record_format	Article
spelling	doaj-367e267342994d21bf78c3183f380d632021-05-07T23:00:40ZengIEEEIEEE Access2169-35362021-01-019664986650810.1109/ACCESS.2021.30765389419373Reinforcement Learning-Based Detection for State Estimation Under False Data InjectionWeiliang Jiang0https://orcid.org/0000-0002-6892-0562Wen Yang1https://orcid.org/0000-0003-4943-7919Jiayu Zhou2https://orcid.org/0000-0001-7510-1015Wenjie Ding3Yue Luo4Yun Liu5https://orcid.org/0000-0002-4230-0736Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, ChinaWe consider the problem of network security under false data injection attacks over wireless sensor networks.To resist the attacks which can inject false data into communication channels according to a certain probability, we formulate the online attack detection problem as a partially observable Markov decision process problem and design a detector for each sensor based on the framework of model-free reinforcement learning. By numerical simulations, we illustrate the effectiveness of the proposed reinforcement learning algorithm and show the performance of the proposed detector compared with the typical detector in the existing works.https://ieeexplore.ieee.org/document/9419373/Wireless sensor networkfalse data injection attackreinforcement learningpartially observable Markov decision process
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Weiliang Jiang Wen Yang Jiayu Zhou Wenjie Ding Yue Luo Yun Liu
spellingShingle	Weiliang Jiang Wen Yang Jiayu Zhou Wenjie Ding Yue Luo Yun Liu Reinforcement Learning-Based Detection for State Estimation Under False Data Injection IEEE Access Wireless sensor network false data injection attack reinforcement learning partially observable Markov decision process
author_facet	Weiliang Jiang Wen Yang Jiayu Zhou Wenjie Ding Yue Luo Yun Liu
author_sort	Weiliang Jiang
title	Reinforcement Learning-Based Detection for State Estimation Under False Data Injection
title_short	Reinforcement Learning-Based Detection for State Estimation Under False Data Injection
title_full	Reinforcement Learning-Based Detection for State Estimation Under False Data Injection
title_fullStr	Reinforcement Learning-Based Detection for State Estimation Under False Data Injection
title_full_unstemmed	Reinforcement Learning-Based Detection for State Estimation Under False Data Injection
title_sort	reinforcement learning-based detection for state estimation under false data injection
publisher	IEEE
series	IEEE Access
issn	2169-3536
publishDate	2021-01-01
description	We consider the problem of network security under false data injection attacks over wireless sensor networks.To resist the attacks which can inject false data into communication channels according to a certain probability, we formulate the online attack detection problem as a partially observable Markov decision process problem and design a detector for each sensor based on the framework of model-free reinforcement learning. By numerical simulations, we illustrate the effectiveness of the proposed reinforcement learning algorithm and show the performance of the proposed detector compared with the typical detector in the existing works.
topic	Wireless sensor network false data injection attack reinforcement learning partially observable Markov decision process
url	https://ieeexplore.ieee.org/document/9419373/
work_keys_str_mv	AT weiliangjiang reinforcementlearningbaseddetectionforstateestimationunderfalsedatainjection AT wenyang reinforcementlearningbaseddetectionforstateestimationunderfalsedatainjection AT jiayuzhou reinforcementlearningbaseddetectionforstateestimationunderfalsedatainjection AT wenjieding reinforcementlearningbaseddetectionforstateestimationunderfalsedatainjection AT yueluo reinforcementlearningbaseddetectionforstateestimationunderfalsedatainjection AT yunliu reinforcementlearningbaseddetectionforstateestimationunderfalsedatainjection
_version_	1721455134345527296

Reinforcement Learning-Based Detection for State Estimation Under False Data Injection

Similar Items