Paper Title: Enhancing IIoT Security Using Hybrid CNN-BiLSTM Models with Blockchain Integration, 2025
Conference Name: 7th International Conference on Artificial Intelligence in Information Communication (ICAIIC 2025)
Abstract: Abstract—In the rapidly evolving Industrial Internet of Things
(IIoT) landscape, ensuring robust security measures for de-
tecting and mitigating cyber threats is paramount. This paper
suggests a decentralized intrusion detection system (IDS) that
uses Federated Learning (FL) integrated with a permissioned
blockchain layer to secure IIoT networks. The system leverages
a modified deep learning architecture, staking Convolutional
Neural Networks (CNN) with Bidirectional Long Short-Term
Memory (BiLSTM) and Long Short-Term Memory (LSTM)
layers to quickly detect the temporal and spatial sequences
in data traffic over a network. Training the model in a fed-
erated environment ensures data privacy, and the blockchain
layer guarantees that only authorized devices participate in the
learning process, adding an extra layer of security. We evaluated
our model using the Edge-IIoTset dataset, containing 14 cyber-
attack types and one benign class. Our suggested model showed
superior performance, achieving an accuracy of 95%, surpassing
traditional models’ accuracy in similar environments.