ML-based categorical boosting with hybrid transfer learning model for enhancing cyber threat intelligence in IoV environment

The increasing complexity of the Internet of Vehicles (IoV) necessitates robust Intrusion Detection Systems (IDS) to protect against cyberattacks. Recent studies show a 60% rise in attacks targeting vehicular communication systems, with 45% attributed to attacks. Existing IoV-based IDS methods face...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of Umm Al-Qura University for Engineering and Architecture
Hlavní autoři: Supriya, Dhanda, Praveen Krishna, Anne Venkata
Médium: Journal Article
Jazyk:angličtina
Vydáno: 17.10.2025
ISSN:2731-6688, 1658-8150
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The increasing complexity of the Internet of Vehicles (IoV) necessitates robust Intrusion Detection Systems (IDS) to protect against cyberattacks. Recent studies show a 60% rise in attacks targeting vehicular communication systems, with 45% attributed to attacks. Existing IoV-based IDS methods face challenges such as imbalanced datasets and limited feature extraction capabilities, which hinder accurate threat detection. The proposed IoV-Net framework addresses these issues by integrating comprehensive data preprocessing, where noise and redundancies in the Canadian Institute for Cybersecurity collected IoV 2024 (CICIoV2024) dataset are eliminated, followed by dimensionality reduction. For feature extraction, the Transfer Learning Adopted Hybrid Inception-ResNetV2 (TLA-HIR) model is employed, leveraging its superior ability to capture both local and global patterns in IoV data. To tackle class imbalance, the Adaptive Synthetic Minority Over-Sampling (ASMOS) technique is introduced, enhancing the dataset with synthetic samples for underrepresented classes, thus preventing overfitting. Finally, the Machine Learning-based Categorical Boosting (MLCB) Classifier is implemented, ensuring high accuracy in attack classification by utilizing gradient boosting and efficient handling of categorical features. This methodology, applied to the CICIoV2024 dataset with the feature analysis on three cases: binary, decimal, and hexadecimal, promises improved detection rates for sophisticated IoV-based attacks with an accuracy of 99.84%, 99.88%, and 99.88%, respectively.
AbstractList The increasing complexity of the Internet of Vehicles (IoV) necessitates robust Intrusion Detection Systems (IDS) to protect against cyberattacks. Recent studies show a 60% rise in attacks targeting vehicular communication systems, with 45% attributed to attacks. Existing IoV-based IDS methods face challenges such as imbalanced datasets and limited feature extraction capabilities, which hinder accurate threat detection. The proposed IoV-Net framework addresses these issues by integrating comprehensive data preprocessing, where noise and redundancies in the Canadian Institute for Cybersecurity collected IoV 2024 (CICIoV2024) dataset are eliminated, followed by dimensionality reduction. For feature extraction, the Transfer Learning Adopted Hybrid Inception-ResNetV2 (TLA-HIR) model is employed, leveraging its superior ability to capture both local and global patterns in IoV data. To tackle class imbalance, the Adaptive Synthetic Minority Over-Sampling (ASMOS) technique is introduced, enhancing the dataset with synthetic samples for underrepresented classes, thus preventing overfitting. Finally, the Machine Learning-based Categorical Boosting (MLCB) Classifier is implemented, ensuring high accuracy in attack classification by utilizing gradient boosting and efficient handling of categorical features. This methodology, applied to the CICIoV2024 dataset with the feature analysis on three cases: binary, decimal, and hexadecimal, promises improved detection rates for sophisticated IoV-based attacks with an accuracy of 99.84%, 99.88%, and 99.88%, respectively.
Author Praveen Krishna, Anne Venkata
Supriya, Dhanda
Author_xml – sequence: 1
  givenname: Dhanda
  surname: Supriya
  fullname: Supriya, Dhanda
– sequence: 2
  givenname: Anne Venkata
  surname: Praveen Krishna
  fullname: Praveen Krishna, Anne Venkata
BookMark eNotkNtKAzEQhoNUsNa-gFd5gdUcNnu4lOKhUPFGvQ3ZZNKNbBNJgrbgw5taL2aGf-bnh_ku0cwHDwhdU3JDCWlvU837XlSElSKs9P0ZmtNGdFVHBZmhOWs5rZqm6y7QMqUPUlxdT7mo5-jneVMNKoHBWmXYhui0mvAQQsrOb_G3yyMeD0N0BueofLIQ8QQq-uN1FwxM2IaIwY_K6-NOH4ZiyWMElbHzGabJbcFrKAKvw3uxfrkY_A58vkLnVk0Jlv9zgd4e7l9XT9Xm5XG9uttUmop-X_VCWz1wwUCXT1hHlGpqUtvGcKOHvjVmMMI03BbFTGtqbgXpW81MLbRhhi8QO-XqGFKKYOVndDsVD5ISeUQoTwhlQSj_EMo9_wU-XWpO
Cites_doi 10.1109/JIOT.2024.3441763
10.1109/JIOT.2024.3414492
10.1109/TVT.2024.3402366
10.1016/j.adhoc.2023.103330
10.1109/VNC61989.2024.10575970
10.1038/s41598-023-50906-7
10.1007/s10207-024-00903-2
10.1109/TVT.2024.3385916
10.1109/ISCS61804.2024.10581038
10.1109/ACCESS.2024.3382992
10.1109/TIFS.2024.3426304
10.1109/OJVT.2024.3422253
10.3390/s22041340
10.1007/978-3-031-68606-1_12
10.32604/cmc.2024.053037
10.1016/j.cose.2024.103962
10.1109/JIOT.2024.3397652
10.1145/3695998
10.1016/j.iot.2024.101209
10.1109/AIIoT61789.2024.10579000
10.1109/ACCESS.2024.3368392
10.1016/j.cose.2024.104067
10.1109/ACCESS.2024.3416840
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.1007/s43995-025-00225-x
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1658-8150
ExternalDocumentID 10_1007_s43995_025_00225_x
GroupedDBID 0R~
AAKKN
AAYXX
ABEEZ
ACACY
ACULB
AFFHD
AFGXO
AFKRA
ALMA_UNASSIGNED_HOLDINGS
BENPR
C24
C6C
CCPQU
CITATION
EBS
GROUPED_DOAJ
M~E
PHGZM
PHGZT
PIMPY
SOJ
ID FETCH-LOGICAL-c159x-95cfcb352ec273280aa6404f6d3dcb97ddbd5d63fdcb2d7d43f5097c2d45cd2d3
ISSN 2731-6688
IngestDate Sat Nov 29 07:05:18 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c159x-95cfcb352ec273280aa6404f6d3dcb97ddbd5d63fdcb2d7d43f5097c2d45cd2d3
OpenAccessLink https://link.springer.com/content/pdf/10.1007/s43995-025-00225-x.pdf
ParticipantIDs crossref_primary_10_1007_s43995_025_00225_x
PublicationCentury 2000
PublicationDate 2025-10-17
PublicationDateYYYYMMDD 2025-10-17
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-17
  day: 17
PublicationDecade 2020
PublicationTitle Journal of Umm Al-Qura University for Engineering and Architecture
PublicationYear 2025
References 225_CR9
MB Anley (225_CR22) 2024; 144
M Almehdhar (225_CR23) 2024; 5
225_CR24
AA Korba (225_CR3) 2024; 73
K Huang (225_CR2) 2024; 147
225_CR19
225_CR18
225_CR14
225_CR17
225_CR11
225_CR10
225_CR13
ECP Neto (225_CR20) 2024; 26
A Verma (225_CR4) 2024; 12
X Han (225_CR25) 2024; 19
NA Amirudin (225_CR15) 2024; 7
225_CR1
J Gao (225_CR8) 2024
MS Korium (225_CR16) 2024; 153
225_CR5
225_CR6
225_CR7
J Prakash (225_CR21) 2024; 14
K Zhang (225_CR12) 2024; 12
References_xml – year: 2024
  ident: 225_CR8
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2024.3441763
– ident: 225_CR7
  doi: 10.1109/JIOT.2024.3414492
– ident: 225_CR10
  doi: 10.1109/TVT.2024.3402366
– volume: 153
  year: 2024
  ident: 225_CR16
  publication-title: ad hoc networks
  doi: 10.1016/j.adhoc.2023.103330
– ident: 225_CR13
  doi: 10.1109/VNC61989.2024.10575970
– volume: 7
  start-page: 1
  issue: 1
  year: 2024
  ident: 225_CR15
  publication-title: Platform J Sci Technol
– volume: 14
  start-page: 468
  issue: 1
  year: 2024
  ident: 225_CR21
  publication-title: Sci Rep
  doi: 10.1038/s41598-023-50906-7
– ident: 225_CR18
  doi: 10.1007/s10207-024-00903-2
– volume: 73
  start-page: 12399
  issue: 9
  year: 2024
  ident: 225_CR3
  publication-title: IEEE Trans Veh Technol
  doi: 10.1109/TVT.2024.3385916
– ident: 225_CR6
  doi: 10.1109/ISCS61804.2024.10581038
– volume: 12
  start-page: 48301
  year: 2024
  ident: 225_CR4
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2024.3382992
– volume: 19
  start-page: 6871
  year: 2024
  ident: 225_CR25
  publication-title: IEEE Trans Inf Forensics Secur
  doi: 10.1109/TIFS.2024.3426304
– volume: 5
  start-page: 869
  year: 2024
  ident: 225_CR23
  publication-title: IEEE Open J Veh Technol
  doi: 10.1109/OJVT.2024.3422253
– ident: 225_CR1
  doi: 10.3390/s22041340
– ident: 225_CR17
– ident: 225_CR9
  doi: 10.1007/978-3-031-68606-1_12
– ident: 225_CR11
  doi: 10.32604/cmc.2024.053037
– volume: 144
  start-page: 103962
  year: 2024
  ident: 225_CR22
  publication-title: Elsevier BV
  doi: 10.1016/j.cose.2024.103962
– ident: 225_CR5
  doi: 10.1109/JIOT.2024.3397652
– ident: 225_CR14
  doi: 10.1145/3695998
– volume: 26
  start-page: 101209
  year: 2024
  ident: 225_CR20
  publication-title: Elsevier BV
  doi: 10.1016/j.iot.2024.101209
– ident: 225_CR24
  doi: 10.1109/AIIoT61789.2024.10579000
– volume: 12
  start-page: 28911
  year: 2024
  ident: 225_CR12
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2024.3368392
– volume: 147
  year: 2024
  ident: 225_CR2
  publication-title: Computers & Security
  doi: 10.1016/j.cose.2024.104067
– ident: 225_CR19
  doi: 10.1109/ACCESS.2024.3416840
SSID ssj0002891354
Score 2.3062959
Snippet The increasing complexity of the Internet of Vehicles (IoV) necessitates robust Intrusion Detection Systems (IDS) to protect against cyberattacks. Recent...
SourceID crossref
SourceType Index Database
Title ML-based categorical boosting with hybrid transfer learning model for enhancing cyber threat intelligence in IoV environment
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1658-8150
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002891354
  issn: 2731-6688
  databaseCode: DOA
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1658-8150
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002891354
  issn: 2731-6688
  databaseCode: M~E
  dateStart: 20190101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1658-8150
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002891354
  issn: 2731-6688
  databaseCode: BENPR
  dateStart: 20250601
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Publicly Available Content Database
  customDbUrl:
  eissn: 1658-8150
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002891354
  issn: 2731-6688
  databaseCode: PIMPY
  dateStart: 20250601
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLink Open Access Journals
  customDbUrl:
  eissn: 1658-8150
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002891354
  issn: 2731-6688
  databaseCode: C24
  dateStart: 20221201
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3PS-NAFB6K68E9yOoqq64yh72FWZofk0mORXZZQcUFLd5KMjOxRR1LWqUF8Q_xr_W9mSYdFGE97KGhCWEa8r7OfPPe-94j5EcSdnUl4Y9UqlyzJAsrVsCyzHSouYDtQ6VsRLd_LE5Ps8vL_KzTeW60MA83wphsNsvH_9XUcA2MjdLZD5i7HRQuwHcwOhzB7HD8J8OfHDNcmlSAuU5XixIgwKUn09bvOpyjTgvbQwBp1XXTOuLK9cVxVcDNECtxoCJ3XmrMRLS-hJFfwXNkgqO7vq-Ve4fqXtzeBr0b9ve-LvxMEPwdrx6ijWP0vMDGMmA1rkdzF5hCR3-7kpxh7yRt7Ew1dOK2HqwbQV-ba6e5az0aka2E6gScbuIDRhWyNHXt_n5qNzEDU2JZ6IrUvpn2XabHBPdWqDeHD1ATzmbLRa4J7L9a-9qMxLZ6sx1jAGMM7Bi4P_kUCZ5juuDJ09J_F2F81zbZax93ocmyysw3j-LxHo_AnH8h6wtz0J5DzAbpaLNJPnvv_yt5bLBDPezQBjsUsUMddmiDHdpgh1rsULApbbFDLXaoww71sQMnFLBDPexskYvfv84P_7BFew4mgQPPWM5lJUsg8FpGWPKpWxRp0k2qVMVKlrlQqlRcpXEFZ5ESKokrYKdCRirhUkUq3iYr5s7ob4SGUgBTUjyTXCdaxgWwzCKDu6QA-srlDgmalzcYuyosg_cttvuhu_fI2hKE38nKtL7X-2RVPkxHk_rA-mgOrOlfAEiTh1k
linkProvider ISSN International Centre
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=ML-based+categorical+boosting+with+hybrid+transfer+learning+model+for+enhancing+cyber+threat+intelligence+in+IoV+environment&rft.jtitle=Journal+of+Umm+Al-Qura+University+for+Engineering+and+Architecture&rft.au=Supriya%2C+Dhanda&rft.au=Praveen+Krishna%2C+Anne+Venkata&rft.date=2025-10-17&rft.issn=2731-6688&rft.eissn=1658-8150&rft_id=info:doi/10.1007%2Fs43995-025-00225-x&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s43995_025_00225_x
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2731-6688&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2731-6688&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2731-6688&client=summon