False data injection attack dataset for classification, identification, and detection for IIoT in Industry 5.0
Data in Brief · 2025-08 · 61 · 111692
DOI: 10.1016/j.dib.2025.111692 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data in Brief, 2025-08. Verfasst von A K M Ahasan Habib und 4 weiteren Autor:innen. Beteiligte Einrichtung: Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor 43600, Malaysia. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Universiti Kebangsaan Malaysia.
Abstract (Originalsprache)
The new Industry 5.0 era of interaction and accessibility has been brought about by the widespread use of Industrial Internet of Things (IIoT) devices, however, it also has uncovered several security issues, with False Data Injection (FDI) attacks being a significant concern. The FDI attacks can interfere with the availability and operation of internet-connected IIoT devices, and pretence a serious security concern to Industry 5.0. To classify, identify, and detect FDI attacks inside IIoT for Industry 5.0 ecosystems presented the UKMNCT_IIoT_FDIA dataset, an independent and comprehensive dataset. The dataset offers an accurate characterization of IoT environments by covering many different kinds of network configurations and scenarios. We provide a methodical examination regarding the UKMNCT_IIoT_FDIA dataset, evaluating its character traits and characteristics that represent the details of actual IIoT systems. To reflect the dynamic nature of FDI attack threats in IIoT, the dataset comprises a range of attack scenarios, combining various approaches and intensities. The approach we employ makes it easier to create and assess effective machine learning (ML) and deep learning (DL) algorithms for efficient FDI attack detections. Additionally, we demonstrate a multifaceted approach to using the UKMNCT_IIoT_FDIA dataset, which includes detection algorithms to quickly address active FDI attacks, detection processes to identify malicious things, and classification approaches to classify attack categories. Extensive investigations and evaluations have proven the effectiveness of these approaches, highlighting their potential to improve the safety standards of IIoT environments in Industry 5.0.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Cyber Security, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor 43600, Malaysia.
- Institute of Computer Science and Digital Innovation, UCSI University Malaysia, Kuala Lumpur, Selangor 56000, Malaysia.
- Department of Computer Science, College of Computer Science and Engineering, Taibah University, Saudi Arabia.
Förderung
- Universiti Kebangsaan Malaysia
Zitieren
APA
Habib, A. K. M. A., Hasan, M. K., Hassan, R., Islam, S., & Abbas, H. S. (2025). False data injection attack dataset for classification, identification, and detection for IIoT in Industry 5.0. Data in Brief, 61, 111692. https://doi.org/10.1016/j.dib.2025.111692
Vancouver
Habib AKMA, Hasan MK, Hassan R, Islam S, Abbas HS. False data injection attack dataset for classification, identification, and detection for IIoT in Industry 5.0. Data in Brief. 2025;61:111692. doi:10.1016/j.dib.2025.111692
BibTeX
@article{Habib2025,
author = {Habib, A K M Ahasan and Hasan, Mohammad Kamrul and Hassan, Rosilah and Islam, Shayla and Abbas, Huda Saleh},
title = {False data injection attack dataset for classification, identification, and detection for IIoT in Industry 5.0},
journal = {Data in Brief},
year = {2025},
volume = {61},
pages = {111692},
doi = {10.1016/j.dib.2025.111692}
}
EUVIMED