|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM338708782 |
| 003 |
DE-627 |
| 005 |
20250303045937.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2022 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1007/s11227-022-04408-4
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1128.xml
|
| 035 |
|
|
|a (DE-627)NLM338708782
|
| 035 |
|
|
|a (NLM)35340686
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Kim, HyunJin
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Industrial network-based behavioral anomaly detection in AI-enabled smart manufacturing
|
| 264 |
|
1 |
|c 2022
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 07.07.2022
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.
|
| 520 |
|
|
|a Existing manufacturing systems are isolated from the outside world to protect their sites and systems. However, following the trend of the 4th Industrial Revolution, manufacturing systems have also increased the connectivity of various domains and the convergence of numerous technologies. These systems are referred to as smart manufacturing systems. However, this trend has increased the challenge of network anomaly detection methods, which are a major approach to network security in smart manufacturing. Existing methods define normality under the premise that network components are static, and network operation is periodic compared to the information technology environment. Therefore, comprehensive and volatile network environments require significant time, cost, and labor to define normality. Consequently, artificial intelligence (AI)-based anomaly detection studies have been actively conducted to solve this problem. However, such studies require manual analysis based on expert knowledge of each site during the preprocessing stage to extract the learning features from the collected network data. To solve the above problems, this study proposes a protocol reverse engineering method corresponding to the preprocessing stage of exiting AI studies. Through this method, existing AI-based anomaly detection studies can directly use the collected network data to learn normality without expert knowledge of the site. Furthermore, non-polling or reporting network operating environments that are rarely studied in the manufacturing security domain are targeted. Finally, we propose an anomaly detection method that uses an external signature, time information, the pattern of time intervals, and classified messages. Thus, the proposed method can detect anomalies in the encrypted contents of the manufacturing protocols
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Anomaly detection
|
| 650 |
|
4 |
|a Network security
|
| 650 |
|
4 |
|a Smart manufacturing system
|
| 700 |
1 |
|
|a Shon, Taeshik
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t The Journal of supercomputing
|d 1998
|g 78(2022), 11 vom: 23., Seite 13554-13563
|w (DE-627)NLM098252410
|x 0920-8542
|7 nnas
|
| 773 |
1 |
8 |
|g volume:78
|g year:2022
|g number:11
|g day:23
|g pages:13554-13563
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1007/s11227-022-04408-4
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 78
|j 2022
|e 11
|b 23
|h 13554-13563
|