• Je něco špatně v tomto záznamu ?

A Hybrid Lightweight System for Early Attack Detection in the IoMT Fog

SS. Hameed, A. Selamat, L. Abdul Latiff, SA. Razak, O. Krejcar, H. Fujita, MN. Ahmad Sharif, S. Omatu

. 2021 ; 21 (24) : . [pub] 20211211

Jazyk angličtina Země Švýcarsko

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/bmc22003030

Grantová podpora
FRGS/1/2018/ICT04/UTM/01/1 Ministry of Higher Education
Vot 4L876 Ministry of Higher Education

Cyber-attack detection via on-gadget embedded models and cloud systems are widely used for the Internet of Medical Things (IoMT). The former has a limited computation ability, whereas the latter has a long detection time. Fog-based attack detection is alternatively used to overcome these problems. However, the current fog-based systems cannot handle the ever-increasing IoMT's big data. Moreover, they are not lightweight and are designed for network attack detection only. In this work, a hybrid (for host and network) lightweight system is proposed for early attack detection in the IoMT fog. In an adaptive online setting, six different incremental classifiers were implemented, namely a novel Weighted Hoeffding Tree Ensemble (WHTE), Incremental K-Nearest Neighbors (IKNN), Incremental Naïve Bayes (INB), Hoeffding Tree Majority Class (HTMC), Hoeffding Tree Naïve Bayes (HTNB), and Hoeffding Tree Naïve Bayes Adaptive (HTNBA). The system was benchmarked with seven heterogeneous sensors and a NetFlow data infected with nine types of recent attack. The results showed that the proposed system worked well on the lightweight fog devices with ~100% accuracy, a low detection time, and a low memory usage of less than 6 MiB. The single-criteria comparative analysis showed that the WHTE ensemble was more accurate and was less sensitive to the concept drift.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22003030
003      
CZ-PrNML
005      
20220127150728.0
007      
ta
008      
220113s2021 sz f 000 0|eng||
009      
AR
024    7_
$a 10.3390/s21248289 $2 doi
035    __
$a (PubMed)34960384
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a sz
100    1_
$a Hameed, Shilan S $u Malaysia-Japan International Institute of Technology (MJIIT), University Teknologi Malaysia, Kuala Lumpur 54100, Malaysia $u Directorate of Information Technology, Koya University, Koya 44023, Iraq
245    12
$a A Hybrid Lightweight System for Early Attack Detection in the IoMT Fog / $c SS. Hameed, A. Selamat, L. Abdul Latiff, SA. Razak, O. Krejcar, H. Fujita, MN. Ahmad Sharif, S. Omatu
520    9_
$a Cyber-attack detection via on-gadget embedded models and cloud systems are widely used for the Internet of Medical Things (IoMT). The former has a limited computation ability, whereas the latter has a long detection time. Fog-based attack detection is alternatively used to overcome these problems. However, the current fog-based systems cannot handle the ever-increasing IoMT's big data. Moreover, they are not lightweight and are designed for network attack detection only. In this work, a hybrid (for host and network) lightweight system is proposed for early attack detection in the IoMT fog. In an adaptive online setting, six different incremental classifiers were implemented, namely a novel Weighted Hoeffding Tree Ensemble (WHTE), Incremental K-Nearest Neighbors (IKNN), Incremental Naïve Bayes (INB), Hoeffding Tree Majority Class (HTMC), Hoeffding Tree Naïve Bayes (HTNB), and Hoeffding Tree Naïve Bayes Adaptive (HTNBA). The system was benchmarked with seven heterogeneous sensors and a NetFlow data infected with nine types of recent attack. The results showed that the proposed system worked well on the lightweight fog devices with ~100% accuracy, a low detection time, and a low memory usage of less than 6 MiB. The single-criteria comparative analysis showed that the WHTE ensemble was more accurate and was less sensitive to the concept drift.
650    _2
$a Bayesova věta $7 D001499
650    _2
$a big data $7 D000077558
650    _2
$a časná diagnóza $7 D042241
650    12
$a internet věcí $7 D000080487
655    _2
$a časopisecké články $7 D016428
700    1_
$a Selamat, Ali $u Malaysia-Japan International Institute of Technology (MJIIT), University Teknologi Malaysia, Kuala Lumpur 54100, Malaysia $u School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Skudai 81310, Malaysia $u Media and Games Center of Excellence (MagicX), Universiti Teknologi Malaysia, Skudai 81310, Malaysia $u Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 50003 Hradec Kralove, Czech Republic
700    1_
$a Abdul Latiff, Liza $u Razak Faculty of Technology and Informatics, Universiti Teknologi Malaysia, Kuala Lumpur 54100, Malaysia
700    1_
$a Razak, Shukor A $u School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia, Skudai 81310, Malaysia
700    1_
$a Krejcar, Ondrej $u Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 50003 Hradec Kralove, Czech Republic
700    1_
$a Fujita, Hamido $u i-SOMET Incorporated Association, Morioka 020-0104, Japan $u Regional Research Center, Iwate Prefectural University, Takizawa 020-0693, Japan
700    1_
$a Ahmad Sharif, Mohammad Nazir $u Institute of IR4.0, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
700    1_
$a Omatu, Sigeru $u Graduate School, Hiroshima University, Kagamiyama, Higashihiroshima 739-8511, Japan
773    0_
$w MED00008309 $t Sensors (Basel, Switzerland) $x 1424-8220 $g Roč. 21, č. 24 (2021)
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34960384 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20220113 $b ABA008
991    __
$a 20220127150725 $b ABA008
999    __
$a ok $b bmc $g 1750716 $s 1154179
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2021 $b 21 $c 24 $e 20211211 $i 1424-8220 $m Sensors $n Sensors Basel $x MED00008309
GRA    __
$a FRGS/1/2018/ICT04/UTM/01/1 $p Ministry of Higher Education
GRA    __
$a Vot 4L876 $p Ministry of Higher Education
LZP    __
$a Pubmed-20220113

Najít záznam

Citační ukazatele

Možnosti archivace