Secure State Estimation for Artificial Neural Networks With Unknown-But-Bounded Noises: A Homomorphic Encryption Scheme

This article is concerned with the secure state estimation problem for artificial neural networks (ANNs) subject to unknown-but-bounded noises, where sensors and the remote estimator are connected via open and bandwidth-limited communication networks. Using the encoding-decoding mechanism (EDM) and...

Full description

Saved in:
Bibliographic Details
Published inIEEE transaction on neural networks and learning systems Vol. 36; no. 4; pp. 6780 - 6791
Main Authors Zhu, Kaiqun, Wang, Zidong, Ding, Derui, Dong, Hongli, Xu, Cheng-Zhong
Format Journal Article
LanguageEnglish
Published United States IEEE 01.04.2025
Subjects
Online AccessGet full text
ISSN2162-237X
2162-2388
2162-2388
DOI10.1109/TNNLS.2024.3389873

Cover

Abstract This article is concerned with the secure state estimation problem for artificial neural networks (ANNs) subject to unknown-but-bounded noises, where sensors and the remote estimator are connected via open and bandwidth-limited communication networks. Using the encoding-decoding mechanism (EDM) and the Paillier encryption technique, a novel homomorphic encryption scheme (HES) is introduced, which aims to ensure the secure transmission of measurement information within communication networks that are constrained by bandwidth. Under this encoding-decoding-based HES, the data being transmitted can be encrypted into ciphertexts comprising finite bits. The emphasis of this research is placed on the development of a secure set-membership state estimation algorithm, which allows for the computation of estimates using encrypted data without the need for decryption, thereby ensuring data security throughout the entire estimation process. Taking into account the unknown-but-bounded noises, the underlying ANN, and the adopted HES, sufficient conditions are determined for the existence of the desired ellipsoidal set. The related secure state estimator gains are then derived by addressing optimization problems using the Lagrange multiplier method. Lastly, an example is presented to verify the effectiveness of the proposed secure state estimation approach.
AbstractList This article is concerned with the secure state estimation problem for artificial neural networks (ANNs) subject to unknown-but-bounded noises, where sensors and the remote estimator are connected via open and bandwidth-limited communication networks. Using the encoding-decoding mechanism (EDM) and the Paillier encryption technique, a novel homomorphic encryption scheme (HES) is introduced, which aims to ensure the secure transmission of measurement information within communication networks that are constrained by bandwidth. Under this encoding-decoding-based HES, the data being transmitted can be encrypted into ciphertexts comprising finite bits. The emphasis of this research is placed on the development of a secure set-membership state estimation algorithm, which allows for the computation of estimates using encrypted data without the need for decryption, thereby ensuring data security throughout the entire estimation process. Taking into account the unknown-but-bounded noises, the underlying ANN, and the adopted HES, sufficient conditions are determined for the existence of the desired ellipsoidal set. The related secure state estimator gains are then derived by addressing optimization problems using the Lagrange multiplier method. Lastly, an example is presented to verify the effectiveness of the proposed secure state estimation approach.This article is concerned with the secure state estimation problem for artificial neural networks (ANNs) subject to unknown-but-bounded noises, where sensors and the remote estimator are connected via open and bandwidth-limited communication networks. Using the encoding-decoding mechanism (EDM) and the Paillier encryption technique, a novel homomorphic encryption scheme (HES) is introduced, which aims to ensure the secure transmission of measurement information within communication networks that are constrained by bandwidth. Under this encoding-decoding-based HES, the data being transmitted can be encrypted into ciphertexts comprising finite bits. The emphasis of this research is placed on the development of a secure set-membership state estimation algorithm, which allows for the computation of estimates using encrypted data without the need for decryption, thereby ensuring data security throughout the entire estimation process. Taking into account the unknown-but-bounded noises, the underlying ANN, and the adopted HES, sufficient conditions are determined for the existence of the desired ellipsoidal set. The related secure state estimator gains are then derived by addressing optimization problems using the Lagrange multiplier method. Lastly, an example is presented to verify the effectiveness of the proposed secure state estimation approach.
This article is concerned with the secure state estimation problem for artificial neural networks (ANNs) subject to unknown-but-bounded noises, where sensors and the remote estimator are connected via open and bandwidth-limited communication networks. Using the encoding-decoding mechanism (EDM) and the Paillier encryption technique, a novel homomorphic encryption scheme (HES) is introduced, which aims to ensure the secure transmission of measurement information within communication networks that are constrained by bandwidth. Under this encoding-decoding-based HES, the data being transmitted can be encrypted into ciphertexts comprising finite bits. The emphasis of this research is placed on the development of a secure set-membership state estimation algorithm, which allows for the computation of estimates using encrypted data without the need for decryption, thereby ensuring data security throughout the entire estimation process. Taking into account the unknown-but-bounded noises, the underlying ANN, and the adopted HES, sufficient conditions are determined for the existence of the desired ellipsoidal set. The related secure state estimator gains are then derived by addressing optimization problems using the Lagrange multiplier method. Lastly, an example is presented to verify the effectiveness of the proposed secure state estimation approach.
Author Zhu, Kaiqun
Ding, Derui
Xu, Cheng-Zhong
Dong, Hongli
Wang, Zidong
Author_xml – sequence: 1
  givenname: Kaiqun
  orcidid: 0000-0002-0658-0806
  surname: Zhu
  fullname: Zhu, Kaiqun
  email: zkqun@163.com
  organization: Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
– sequence: 2
  givenname: Zidong
  orcidid: 0000-0002-9576-7401
  surname: Wang
  fullname: Wang, Zidong
  email: Zidong.Wang@brunel.ac.uk
  organization: Department of Computer Science, Brunel University London, Uxbridge, Middlesex, U.K
– sequence: 3
  givenname: Derui
  orcidid: 0000-0001-7402-6682
  surname: Ding
  fullname: Ding, Derui
  email: deruiding2010@usst.edu.cn
  organization: Department of Control Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China
– sequence: 4
  givenname: Hongli
  orcidid: 0000-0001-8531-6757
  surname: Dong
  fullname: Dong, Hongli
  email: shiningdhl@vip.126.com
  organization: Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China
– sequence: 5
  givenname: Cheng-Zhong
  orcidid: 0000-0001-9480-0356
  surname: Xu
  fullname: Xu, Cheng-Zhong
  email: czxu@um.edu.mo
  organization: Department of Computer and Information Science, State Key Laboratory of Internet of Things for Smart City, University of Macau, Macau, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38656844$$D View this record in MEDLINE/PubMed
BookMark eNp9kc1uEzEUhS1U1JbSF0AIeclmgv9mxsMurQJFitJFWtGd5fFcK6YzdrA9ivr2TJMUIRa1F_fq6nxncc47dOKDB4Q-UDKjlDRf7lar5XrGCBMzzmUja_4GnTNasYJxKU_-7vXDGbpM6ReZXkXKSjSn6IzLqqykEOdotwYzRsDrrDPgRcpu0NkFj22IeB6zs8443eMVjHE_8i7Ex4R_urzB9_7Rh50vrsZcXIXRd9DhVXAJ0lc8xzdhmH7cbpzBC2_i03ZvvDYbGOA9emt1n-DyOC_Q_bfF3fVNsbz9_uN6viwMb6pcWGu41dR0tC4Z11Q3Xcs73taUNVUroBSMEdPpRkzH0ras5DVYXnJr-XSn_AJ9PvhuY_g9QspqcMlA32sPYUyKE1GVlDJBJumno3RsB-jUNk5ZxCf1EtYkkAeBiSGlCFYZl_dp5ahdryhRz9WofTXquRp1rGZC2X_oi_ur0McD5ADgH6AktRSS_wEzv5uD
CODEN ITNNAL
CitedBy_id crossref_primary_10_1007_s11277_024_11565_7
Cites_doi 10.1080/21642583.2023.2173682
10.1109/TCYB.2020.3025932
10.1016/j.neucom.2022.11.079
10.1080/21642583.2022.2158959
10.1080/00207721.2020.1871528
10.1007/978-0-8176-4606-6
10.53941/ijndi.2023.100015
10.1016/j.neucom.2023.01.066
10.1109/TNNLS.2021.3102127
10.1109/TII.2020.3030709
10.1109/TAC.2013.2283096
10.1080/00207721.2022.2055192
10.1109/TCYB.2022.3165041
10.1109/JPROC.2016.2558521
10.1109/TIE.2003.812470
10.1109/TNNLS.2021.3053652
10.1109/TCYB.2022.3209793
10.1016/j.automatica.2021.110154
10.1109/TNNLS.2022.3192346
10.1109/TCYB.2022.3202486
10.1109/MCS.2021.3062956
10.1109/TNSE.2023.3237639
10.53941/ijndi0201007
10.1080/00207721.2022.2122904
10.1016/j.jfranklin.2021.02.035
10.1007/3-540-48910-X_16
10.1109/TAC.2021.3069388
10.1016/j.neucom.2022.10.020
10.1016/j.neucom.2018.02.060
10.1080/21642583.2023.2247007
10.1016/j.automatica.2020.109182
10.53941/ijndi.2023.100018
10.1109/TCYB.2020.3003752
10.1109/tcyb.2023.3239368
10.1109/TCSII.2021.3073724
10.1109/TAC.2022.3140384
10.1016/j.neucom.2022.06.074
10.1109/TNNLS.2022.3174880
10.1080/00207721.2023.2241957
10.1080/00207721.2023.2216274
10.1016/j.inffus.2019.07.008
10.1109/TII.2019.2929747
10.1007/s12555-021-0676-x
10.1016/S1474-6670(17)58301-9
10.1038/s41467-019-12490-1
10.1109/TKDE.2022.3176466
10.1109/TCYB.2021.3049858
10.53941/ijndi0201003
10.1016/j.neunet.2022.02.028
10.1016/j.ins.2022.10.018
10.1145/3561387
10.1109/TAC.2022.3217022
10.1016/j.automatica.2017.10.022
10.1109/TSMC.2020.3035173
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7X8
DOI 10.1109/TNNLS.2024.3389873
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic

PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Xplore Digital Libary (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2162-2388
EndPage 6791
ExternalDocumentID 38656844
10_1109_TNNLS_2024_3389873
10507848
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Alexander von Humboldt Foundation of Germany
  funderid: 10.13039/100005156
– fundername: Science and Technology Development Fund, Macau, SAR
  grantid: 0123/2022/AFJ; 0081/2022/A2
– fundername: Royal Society of the U.K.
  funderid: 10.13039/501100000288
– fundername: Shanghai Pujiang Program
  grantid: 22PJ1411700
– fundername: National Natural Science Foundation of China
  grantid: 61933007; U21A2019
  funderid: 10.13039/501100001809
– fundername: Hainan Province Science and Technology Special Fund of China
  grantid: ZDYF2022SHFZ105
– fundername: University of Macau (UM) Talent Program
  grantid: UMTP2023-PF01-0046
– fundername: China Postdoctoral Science Foundation
  grantid: 2023M732322
  funderid: 10.13039/501100002858
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IFIPE
IPLJI
JAVBF
M43
MS~
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
NPM
RIG
7X8
ID FETCH-LOGICAL-c396t-ffc3fa1cd17523a1a9db3d3b71296b4e54220cda94d3b5fb2537ef353ff30cd13
IEDL.DBID RIE
ISSN 2162-237X
2162-2388
IngestDate Sun Sep 28 07:18:32 EDT 2025
Sun Apr 06 01:21:23 EDT 2025
Thu Apr 24 23:00:07 EDT 2025
Wed Oct 01 06:34:52 EDT 2025
Wed Aug 27 02:04:58 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 4
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c396t-ffc3fa1cd17523a1a9db3d3b71296b4e54220cda94d3b5fb2537ef353ff30cd13
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0000-0002-9576-7401
0000-0001-9480-0356
0000-0001-7402-6682
0000-0002-0658-0806
0000-0001-8531-6757
PMID 38656844
PQID 3046511240
PQPubID 23479
PageCount 12
ParticipantIDs pubmed_primary_38656844
crossref_citationtrail_10_1109_TNNLS_2024_3389873
proquest_miscellaneous_3046511240
ieee_primary_10507848
crossref_primary_10_1109_TNNLS_2024_3389873
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2025-04-01
PublicationDateYYYYMMDD 2025-04-01
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-04-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle IEEE transaction on neural networks and learning systems
PublicationTitleAbbrev TNNLS
PublicationTitleAlternate IEEE Trans Neural Netw Learn Syst
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref12
Durieu (ref15) 1996; 29
ref56
Xiao (ref39) 2023; 528
ref14
ref53
ref52
ref11
ref55
ref10
ref54
ref17
ref16
Paillier (ref33) 1999
ref19
Yi (ref43) 2023; 54
ref51
ref50
ref46
ref48
ref44
Xu (ref40) 2022; 138
ref49
ref8
Yuan (ref45) 2019; 10
ref7
ref9
ref4
ref6
ref5
Liu (ref30) 2022; 150
ref34
ref37
Liu (ref29) 2018; 291
ref36
ref31
ref32
ref2
ref1
ref38
Zhang (ref47) 2021; 358
Yang (ref42) 2022; 503
Boyd (ref3) 1994
ref24
ref23
ref25
ref20
ref22
Yang (ref41) 2022; 53
Gao (ref18) 2023; 21
Reddy (ref35) 2023; 11
ref28
ref27
Huang (ref21) 2020; 121
Li (ref26) 2023; 54
References_xml – ident: ref16
  doi: 10.1080/21642583.2023.2173682
– ident: ref37
  doi: 10.1109/TCYB.2020.3025932
– ident: ref24
  doi: 10.1016/j.neucom.2022.11.079
– ident: ref20
  doi: 10.1080/21642583.2022.2158959
– volume: 54
  start-page: 2875
  issue: 15
  year: 2023
  ident: ref26
  article-title: Dynamic event-triggered distributed filtering design for interval type-2 fuzzy systems over sensor networks under deception attacks
  publication-title: Int. J. Syst. Sci.
  doi: 10.1080/00207721.2020.1871528
– ident: ref2
  doi: 10.1007/978-0-8176-4606-6
– ident: ref52
  doi: 10.53941/ijndi.2023.100015
– volume: 528
  start-page: 217
  year: 2023
  ident: ref39
  article-title: Anti-synchronization for Markovian neural networks via asynchronous intermittent control
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2023.01.066
– ident: ref55
  doi: 10.1109/TNNLS.2021.3102127
– ident: ref5
  doi: 10.1109/TII.2020.3030709
– ident: ref23
  doi: 10.1109/TAC.2013.2283096
– volume: 53
  start-page: 2742
  issue: 13
  year: 2022
  ident: ref41
  article-title: L2-L∞ state estimation for continuous stochastic delayed neural networks via memory event-triggering strategy
  publication-title: Int. J. Syst. Sci.
  doi: 10.1080/00207721.2022.2055192
– ident: ref51
  doi: 10.1109/TCYB.2022.3165041
– ident: ref56
  doi: 10.1109/JPROC.2016.2558521
– ident: ref32
  doi: 10.1109/TIE.2003.812470
– ident: ref12
  doi: 10.1109/TNNLS.2021.3053652
– ident: ref19
  doi: 10.1109/TCYB.2022.3209793
– volume: 138
  year: 2022
  ident: ref40
  article-title: On extended state estimation for nonlinear uncertain systems with round-robin protocol
  publication-title: Automatica
  doi: 10.1016/j.automatica.2021.110154
– ident: ref50
  doi: 10.1109/TNNLS.2022.3192346
– ident: ref7
  doi: 10.1109/TCYB.2022.3202486
– ident: ref11
  doi: 10.1109/MCS.2021.3062956
– ident: ref49
  doi: 10.1109/TNSE.2023.3237639
– ident: ref38
  doi: 10.53941/ijndi0201007
– ident: ref53
  doi: 10.1080/00207721.2022.2122904
– volume: 358
  start-page: 3554
  issue: 7
  year: 2021
  ident: ref47
  article-title: Event-triggered H∞ control for networked spar-type floating production platforms with active tuned heave plate mechanisms and deception attacks
  publication-title: J. Franklin Inst.
  doi: 10.1016/j.jfranklin.2021.02.035
– volume-title: Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
  year: 1999
  ident: ref33
  doi: 10.1007/3-540-48910-X_16
– ident: ref44
  doi: 10.1109/TAC.2021.3069388
– ident: ref8
  doi: 10.1016/j.neucom.2022.10.020
– volume: 291
  start-page: 35
  year: 2018
  ident: ref29
  article-title: Quantized state estimation for neural networks with cyber attacks and hybrid triggered communication scheme
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.02.060
– ident: ref17
  doi: 10.1080/21642583.2023.2247007
– volume: 121
  year: 2020
  ident: ref21
  article-title: Secure remote state estimation against linear man-in-the-middle attacks using watermarking
  publication-title: Automatica
  doi: 10.1016/j.automatica.2020.109182
– ident: ref22
  doi: 10.53941/ijndi.2023.100018
– ident: ref28
  doi: 10.1109/TCYB.2020.3003752
– ident: ref27
  doi: 10.1109/tcyb.2023.3239368
– ident: ref34
  doi: 10.1109/TCSII.2021.3073724
– ident: ref54
  doi: 10.1109/TAC.2022.3140384
– volume: 503
  start-page: 162
  year: 2022
  ident: ref42
  article-title: Event-triggered privacy-preserving bipartite consensus for multi-agent systems based on encryption
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2022.06.074
– volume: 11
  issue: 1
  year: 2023
  ident: ref35
  article-title: Hybrid AC/DC control techniques with improved harmonic conditions using DBN based fuzzy controller and compensator modules
  publication-title: Syst. Sci. Control Eng.
– ident: ref10
  doi: 10.1109/TNNLS.2022.3174880
– ident: ref14
  doi: 10.1080/00207721.2023.2241957
– volume: 54
  start-page: 2059
  issue: 9
  year: 2023
  ident: ref43
  article-title: Probability-guaranteed state estimation for nonlinear delayed systems under mixed attacks
  publication-title: Int. J. Syst. Sci.
  doi: 10.1080/00207721.2023.2216274
– ident: ref4
  doi: 10.1016/j.inffus.2019.07.008
– ident: ref48
  doi: 10.1109/TII.2019.2929747
– volume: 21
  start-page: 684
  issue: 2
  year: 2023
  ident: ref18
  article-title: Robust resilient H∞ state estimation for time-varying recurrent neural networks subject to probabilistic quantization under variance constraint
  publication-title: Int. J. Control, Autom. Syst.
  doi: 10.1007/s12555-021-0676-x
– volume: 29
  start-page: 3975
  issue: 1
  year: 1996
  ident: ref15
  article-title: Trace versus determinant in ellipsoidal outer-bounding, with application to state estimation
  publication-title: IFAC Proc. Volumes
  doi: 10.1016/S1474-6670(17)58301-9
– volume: 10
  start-page: 1
  issue: 1
  year: 2019
  ident: ref45
  article-title: Data driven discovery of cyber physical systems
  publication-title: Nature Commun.
  doi: 10.1038/s41467-019-12490-1
– ident: ref31
  doi: 10.1109/TKDE.2022.3176466
– ident: ref36
  doi: 10.1109/TCYB.2021.3049858
– ident: ref25
  doi: 10.53941/ijndi0201003
– volume-title: System and Control Theory
  year: 1994
  ident: ref3
  article-title: Linear matrix inequal
– volume: 150
  start-page: 181
  year: 2022
  ident: ref30
  article-title: Synchronization and state estimation for discrete-time coupled delayed complex-valued neural networks with random system parameters
  publication-title: Neural Netw.
  doi: 10.1016/j.neunet.2022.02.028
– ident: ref9
  doi: 10.1016/j.ins.2022.10.018
– ident: ref6
  doi: 10.1145/3561387
– ident: ref46
  doi: 10.1109/TAC.2022.3217022
– ident: ref1
  doi: 10.1016/j.automatica.2017.10.022
– ident: ref13
  doi: 10.1109/TSMC.2020.3035173
SSID ssj0000605649
Score 2.5423927
Snippet This article is concerned with the secure state estimation problem for artificial neural networks (ANNs) subject to unknown-but-bounded noises, where sensors...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 6780
SubjectTerms Artificial neural networks
Artificial neural networks (ANNs)
Bandwidth
bandwidth constraints
Cryptography
Encryption
homomorphic encryption scheme (HES)
Noise
secure state estimation
Security
set-membership state estimation
State estimation
Title Secure State Estimation for Artificial Neural Networks With Unknown-But-Bounded Noises: A Homomorphic Encryption Scheme
URI https://ieeexplore.ieee.org/document/10507848
https://www.ncbi.nlm.nih.gov/pubmed/38656844
https://www.proquest.com/docview/3046511240
Volume 36
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore Digital Libary (IEL)
  customDbUrl:
  eissn: 2162-2388
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000605649
  issn: 2162-237X
  databaseCode: RIE
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELZoT1xoCwUWKDISN-QlsR0n4dZWW60Q5EJX7C3yY6yuoAnqJqrg1zN2khVUKkI5JLLsPDTj-JvxzHyEvE01IG7zmnknNQsrNCsRZTOXSu64Lb0WIcH5c6WWK_lxna3HZPWYCwMAMfgM5uEy7uW71vbBVYYzHNFLIYs9spcXakjW2jlUEgTmKsJdnirOuMjXU5JMUr6_rKpPX9Ac5HKORhka2oFAJ_BdqkLKv9akSLJyP96M687FAammNx7CTb7N-87M7a87xRz_-5MOyaMRgdLTQWWOyANoHpODid2BjpP9CbmNrnigEY7SBf4KhixHijA3jh5qT9BQ3iOeYjz5ln7ddFd01QRnXcPO-o6dBeYmcLRqN1vYfqCndNle44ES3li6aOzNz_jfwkdfwTUck9XF4vJ8yUaaBmZFqTrmvRVep9YhEuFCp7p0RjhhcoQSykjIJOeJdbqU2Jh5wzORgxeZ8F5geyqekv2mbeA5oSYHxGumMKnJpAXsLhVYpbUDm_vczUg6Caq2Yw3zQKXxvY62TFLWUc51kHM9ynlG3u3G_BgqePyz93EQ0h89B_nMyJtJIWqcgGFXRTfQ9ts6bC0H1CqTGXk2aMpu9KRgL-6560vykAc-4RgJ9Irsdzc9nCDI6czrqNy_AX1F954
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELagHOBCCxS6UMBI3JCXxHaSTW9ttdUC21zYFXuL_BirK9oEdROh9tczdpIVIBWhHBJZdh6acfzNeGY-Qt7HChC3OcWclYr5FZrliLKZjSW33OROCZ_gfF6ks6X8vEpWfbJ6yIUBgBB8BmN_GfbybW1a7yrDGY7oZSIn98mDREqZdOlaW5dKhNA8DYCXxylnXGSrIU0myj8uimL-FQ1CLsdolqGp7Sl0PONlOpHyj1Up0KzcjTjDynO2S4rhnbuAk-_jttFjc_tXOcf__qg98rjHoPS4U5on5B5UT8nuwO9A--n-jPwMznigAZDSKf4MujxHikA3jO6qT1Bf4COcQkT5hn5bNxd0WXl3XcVO2oadeO4msLSo1xvYHNFjOquv8EAZrw2dVub6Jvy58NEXcAX7ZHk2XZzOWE_UwIzI04Y5Z4RTsbGIRbhQscqtFlboDMFEqiUkkvPIWJVLbEyc5onIwIlEOCewPRbPyU5VV3BAqM4AEZue6Fgn0gB2lymYVCkLJnOZHZF4EFRp-irmnkzjsgzWTJSXQc6ll3PZy3lEPmzH_OhqePyz974X0m89O_mMyLtBIUqcgn5fRVVQt5vSby573CqjEXnRacp29KBgL--461vycLY4n5fzT8WXV-QR9-zCIS7okOw01y28RsjT6DdB0X8Bl1b66w
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Secure+State+Estimation+for+Artificial+Neural+Networks+With+Unknown-But-Bounded+Noises%3A+A+Homomorphic+Encryption+Scheme&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Zhu%2C+Kaiqun&rft.au=Wang%2C+Zidong&rft.au=Ding%2C+Derui&rft.au=Dong%2C+Hongli&rft.date=2025-04-01&rft.pub=IEEE&rft.issn=2162-237X&rft.volume=36&rft.issue=4&rft.spage=6780&rft.epage=6791&rft_id=info:doi/10.1109%2FTNNLS.2024.3389873&rft_id=info%3Apmid%2F38656844&rft.externalDocID=10507848
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon