AUTHOR=Eshmawi Ala' Abdulmajid , Aldrees Asma , Alharthi Raed 

TITLE=Smart framework for industrial IoT and cloud computing network intrusion detection using a ConvLSTM-based deep learning model

JOURNAL=Frontiers in Computer Science

VOLUME=Volume 7 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2025.1622382

DOI=10.3389/fcomp.2025.1622382

ISSN=2624-9898

ABSTRACT=In the rapidly evolving landscape of the Industrial Internet of Things (IIoT) and cloud computing, ensuring robust network security has become a major challenge for the Internet of Everything (IoE). However, this technological advancement has also introduced new vulnerabilities, making these systems prime targets for sophisticated cyberattacks. Ensuring the security of IIoT and cloud networks is critical to protecting sensitive data and maintaining industrial operations' integrity. This study examines data anonymity, security, and preservation in the Edge IIoT environment, focusing on cloud computing and cyber-physical systems. The integration of blockchain in industrial applications introduces additional security risks. This paper uses the EdgeIIoT dataset, enriched with security threat detection features for blockchain environments. The ConvLSTM framework, which uses the characteristics of two deep neural network models, CNN and LSTM, predicts and mitigates threats in IoT, IIoT, and cloud environments. The ConvLSTM model shows outstanding results for accuracy, precision, recall, and F1 score on multiple datasets based on network intrusion detection, showcasing its robustness and generalizability. The results are compared with previously published research work in this domain to demonstrate the superiority of the proposed framework.