Optimizing Intrusion Detection for DoS, DDoS, and Mirai Attacks Subtypes Using Hierarchical Feature Selection and CatBoost on the CICIoT2023 Dataset

Introduction: Modern networks suffer until unheard of vulnerabilities that need for advanced intrusion detection systems (IDS) given the growing danger presented by DoS, DDoS, and Mirai attacks. Research on the identification of certain attack subtypes is still lacking even with the CICIoT2023 datas...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Data & metadata Ročník 3; s. 577
Hlavní autoři: Hajjouz, Abdulkader, Avksentieva, Elena
Médium: Journal Article
Jazyk:angličtina
Vydáno: 17.12.2024
ISSN:2953-4917, 2953-4917
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Introduction: Modern networks suffer until unheard of vulnerabilities that need for advanced intrusion detection systems (IDS) given the growing danger presented by DoS, DDoS, and Mirai attacks. Research on the identification of certain attack subtypes is still lacking even with the CICIoT2023 dataset, which offers a complete basis for evaluating these cyber hazards. Usually, aggregating attacks into more general categories, existing research neglects the complex characteristics of specific subtypes, therefore reducing the detection effectiveness.Methods: This work presents a novel IDS model aiming at high accuracy detection of DoS, DDoS, and Mirai attack subtypes. Using hierarchical feature selection and the CatBoost algorithm on the CICIoT2023 dataset, our model addresses the problems of high-dimensional data and emphasizes on keeping the most important features by means of advanced preprocessing methods including Spearman correlation and hierarchical clustering. Furthermore, used is stratified sampling to guarantee in the training and testing stages fair representation of attack types, both common and uncommon.Results: With an amazing Prediction Time per Network Flow of 7.16e-07 seconds, our model shows a breakthrough in intrusion detection performance by means of rigorous stratified cross-valuation, thereby attaining outstanding outcomes in accuracy, recall, and precision.Conclusions: Our method not only closes a significant gap in current knowledge but also establishes a new benchmark in cybersecurity by providing very detailed protection mechanisms against advanced threats. This study marks major progress in network security as it gives companies a more efficient instrument to recognize and minimize certain cyber risks with better precision and effectiveness
AbstractList Introduction: Modern networks suffer until unheard of vulnerabilities that need for advanced intrusion detection systems (IDS) given the growing danger presented by DoS, DDoS, and Mirai attacks. Research on the identification of certain attack subtypes is still lacking even with the CICIoT2023 dataset, which offers a complete basis for evaluating these cyber hazards. Usually, aggregating attacks into more general categories, existing research neglects the complex characteristics of specific subtypes, therefore reducing the detection effectiveness.Methods: This work presents a novel IDS model aiming at high accuracy detection of DoS, DDoS, and Mirai attack subtypes. Using hierarchical feature selection and the CatBoost algorithm on the CICIoT2023 dataset, our model addresses the problems of high-dimensional data and emphasizes on keeping the most important features by means of advanced preprocessing methods including Spearman correlation and hierarchical clustering. Furthermore, used is stratified sampling to guarantee in the training and testing stages fair representation of attack types, both common and uncommon.Results: With an amazing Prediction Time per Network Flow of 7.16e-07 seconds, our model shows a breakthrough in intrusion detection performance by means of rigorous stratified cross-valuation, thereby attaining outstanding outcomes in accuracy, recall, and precision.Conclusions: Our method not only closes a significant gap in current knowledge but also establishes a new benchmark in cybersecurity by providing very detailed protection mechanisms against advanced threats. This study marks major progress in network security as it gives companies a more efficient instrument to recognize and minimize certain cyber risks with better precision and effectiveness
Author Hajjouz, Abdulkader
Avksentieva, Elena
Author_xml – sequence: 1
  givenname: Abdulkader
  orcidid: 0000-0002-8256-6790
  surname: Hajjouz
  fullname: Hajjouz, Abdulkader
– sequence: 2
  givenname: Elena
  orcidid: 0000-0001-5000-4868
  surname: Avksentieva
  fullname: Avksentieva, Elena
BookMark eNpNkM9OAjEYxBujiYhcfIKejav9y7ZH3BXZBMMBOG-63VaqsCVtOeBz-MACEuPlm5nD_PJlbsBl5zsDwB1Gj3xIJHtqNwQRxvP8AvSI5DRjEueX__w1GMT4gRCiFFNGeQ98z7bJbdyX695h1aWwi853sDTJ6HR01gdY-vkDLE9XdS18c0E5OEpJ6c8I57sm7bcmwmU8MibOBBX0ymm1hmOj0i4YODfrM-7YL1R69j4meMhpZWBRFZVfHD6nsFRJRZNuwZVV62gGZ-2D5fhlUUyy6ey1KkbTTGPEUybanKtGECJbhoi0QmorGo2xpVY3cthyYaSinNAci2HOiGWaUMKZzEWLFaJ9cP_L1cHHGIytt8FtVNjXGNWnSeu_SekPG1pqYg
Cites_doi 10.1186/s42400-019-0038-7
10.1016/j.iot.2024.101336
10.1016/j.isatra.2021.01.036
10.1093/cybsec/tyy006
10.1177/0890334420906850
10.3390/electronics11193079
10.1007/s13369-019-04319-2
10.7717/peerj-cs.1569
10.3390/electronics12061333
10.1109/INCET61516.2024.10593167
10.1007/s42979-022-01031-1
10.1109/JSTARS.2021.3063507
10.1016/j.cose.2023.103597
10.17762/ijcnis.v13i2.4943
10.1109/TCYB.2022.3151880
10.1109/DICCT61038.2024.10533028
10.3390/s23135941
10.1002/itl2.305
10.1007/s12046-020-1308-5
10.1186/s40537-020-00369-8
10.1007/s10115-023-02010-5
10.1016/j.prime.2024.100673
10.1186/s42400-021-00077-7
10.3390/electronics11193133
10.3389/fnano.2022.972421
10.1016/j.cose.2023.103096
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.56294/dm2024577
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
EISSN 2953-4917
ExternalDocumentID 10_56294_dm2024577
GroupedDBID AAFWJ
AAYXX
ABDBF
ALMA_UNASSIGNED_HOLDINGS
CITATION
EAP
ESX
FAEIB
M~E
ID FETCH-LOGICAL-c105t-8d75ab8229d4029f89cf8bc11f3fcb96d58e9a35237186742f4c23254978d1a03
ISSN 2953-4917
IngestDate Sat Nov 29 05:10:31 EST 2025
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c105t-8d75ab8229d4029f89cf8bc11f3fcb96d58e9a35237186742f4c23254978d1a03
ORCID 0000-0001-5000-4868
0000-0002-8256-6790
ParticipantIDs crossref_primary_10_56294_dm2024577
PublicationCentury 2000
PublicationDate 2024-12-17
PublicationDateYYYYMMDD 2024-12-17
PublicationDate_xml – month: 12
  year: 2024
  text: 2024-12-17
  day: 17
PublicationDecade 2020
PublicationTitle Data & metadata
PublicationYear 2024
References 12639
12659
12652
12653
12650
12651
12657
12654
12655
cr-split#-12658.2
cr-split#-12658.1
cr-split#-12656.2
cr-split#-12656.1
12660
12649
12647
12648
12641
12663
12642
12664
12661
12640
12662
12645
12667
12646
12668
12643
12665
12644
12666
References_xml – ident: 12652
  doi: 10.1186/s42400-019-0038-7
– ident: 12655
  doi: 10.1016/j.iot.2024.101336
– ident: #cr-split#-12656.2
– ident: 12639
  doi: 10.1016/j.isatra.2021.01.036
– ident: 12668
– ident: 12646
  doi: 10.1093/cybsec/tyy006
– ident: 12664
  doi: 10.1177/0890334420906850
– ident: 12650
  doi: 10.3390/electronics11193079
– ident: 12663
– ident: 12651
  doi: 10.1007/s13369-019-04319-2
– ident: #cr-split#-12658.2
– ident: 12660
  doi: 10.7717/peerj-cs.1569
– ident: 12645
  doi: 10.3390/electronics12061333
– ident: #cr-split#-12656.1
  doi: 10.1109/INCET61516.2024.10593167
– ident: 12661
– ident: 12649
  doi: 10.1007/s42979-022-01031-1
– ident: 12666
  doi: 10.1109/JSTARS.2021.3063507
– ident: 12643
  doi: 10.1016/j.cose.2023.103597
– ident: 12641
  doi: 10.17762/ijcnis.v13i2.4943
– ident: 12640
  doi: 10.1109/TCYB.2022.3151880
– ident: #cr-split#-12658.1
  doi: 10.1109/DICCT61038.2024.10533028
– ident: 12654
  doi: 10.3390/s23135941
– ident: 12642
  doi: 10.1002/itl2.305
– ident: 12648
  doi: 10.1007/s12046-020-1308-5
– ident: 12665
  doi: 10.1186/s40537-020-00369-8
– ident: 12662
  doi: 10.1007/s10115-023-02010-5
– ident: 12659
  doi: 10.1016/j.prime.2024.100673
– ident: 12653
  doi: 10.1186/s42400-021-00077-7
– ident: 12644
  doi: 10.3390/electronics11193133
– ident: 12657
– ident: 12667
  doi: 10.3389/fnano.2022.972421
– ident: 12647
  doi: 10.1016/j.cose.2023.103096
SSID ssj0003313435
Score 2.2843444
Snippet Introduction: Modern networks suffer until unheard of vulnerabilities that need for advanced intrusion detection systems (IDS) given the growing danger...
SourceID crossref
SourceType Index Database
StartPage 577
Title Optimizing Intrusion Detection for DoS, DDoS, and Mirai Attacks Subtypes Using Hierarchical Feature Selection and CatBoost on the CICIoT2023 Dataset
Volume 3
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2953-4917
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0003313435
  issn: 2953-4917
  databaseCode: M~E
  dateStart: 20220101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLfK4MAFDQHia5MluJWIJrYb-9i1oO3AQKJIu1VxbEthbTKtppo4cOfOH8zzR9xucBgHLm77lJe2-f30_Gy_D4RewxRLNOUmo5KNMmqEzITRLJPgaijDS5Er7ptNlKen_OxMfBoMfva5MJtl2bb86kpc_FeoQQZgu9TZf4A73RQE8B5AhxFgh_FWwH8EI7BqvodIAJdS4QCeaavrFFY463zA3iy--liL5rJqhhNrXc69Mydub3Y9DBEFx41LU_ZdU5ZD5zS6U4fPvoNOH808rexR161tPHwYTk-mJ93cdU0HYlmYKq-dATiRJ91K2yqmx0VD-BX-pN_Unkj1bXnuAq0TKTfnLlWq0ZsqRKTp0Pq737UofG3EkKQZjFshGMmoiCL9F1m0zmTHurLQ8eWm1QcXTlCARa3cN8WLrpfWvjHlpUBEWAJ57UXSvYPuFiUTLjrww4_tdh0hOaG-XWv6laHYrVd_m9R33JsdP2W-jx7EBQaeBGI8RAPdPkK_tqTAiRQ4kQIDKTCQ4Q2e-REAxZ4QOBIC94TAnhB4lxA4EgInQnj9nhAYPgMh8JYQOBLiMfry_t18epzFfhxZDV64zbgqWSVdhwBFR4UwXNSGyzrPDTG1FGPFuBYVePSkdGUSaWFoDQ47c00MVV6NyBO013atfoowYxpWDpJSJce0NkRQRcejUlScaclk-Qy96h_j4iKUXVn8idXzW131At3fMvAl2oOHrA_QvXpjm_XloYf5N2HKdk8
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=Optimizing+Intrusion+Detection+for+DoS%2C+DDoS%2C+and+Mirai+Attacks+Subtypes+Using+Hierarchical+Feature+Selection+and+CatBoost+on+the+CICIoT2023+Dataset&rft.jtitle=Data+%26+metadata&rft.au=Hajjouz%2C+Abdulkader&rft.au=Avksentieva%2C+Elena&rft.date=2024-12-17&rft.issn=2953-4917&rft.eissn=2953-4917&rft.volume=3&rft.spage=577&rft_id=info:doi/10.56294%2Fdm2024577&rft.externalDBID=n%2Fa&rft.externalDocID=10_56294_dm2024577
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2953-4917&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2953-4917&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2953-4917&client=summon