A predominant intrusion detection system in IIoT using ELCG-DSA AND LWS-BiOLSTM with blockchain

The growing connectivity of Industrial Internet of Things (IIoT) systems has increased cyber threats, necessitating early detection of intrusions. However, existing systems often lack focus on intermediate and continuous multifactor authorization between IIoT and Industrial Control Systems (ICS). To overcome this, an efficient IDS for IIoT using an Exponential Linear Congruential Generator - Digital Signature Algorithm (ELCG-DSA) and Log Wave Sigmoid-Bidirectional Once Long Short-Term Memory (LWS-BiOLSTM) is proposed. Initially, the industry and vehicle details are registered in the blockchain network, and the Polychoric Entropy Correlation-Tiger Hashing Algorithm (PEC-Tiger) generates hash codes through smart contract creation. From the generated hash codes, a partial digital signature is created by using the ELCG-DSA technique. After login, the registered details are processed for enhancing security using Montgomery Modulo Curve Cryptography (MMCC). Then, the details are verified by using PEC-Tiger, and if the hash code matches, the key generation centre is notified for the creation of a fully digital signature. After verification, the Luus–Jaakola Sequence-based Pelican Optimization Algorithm (LJS-POA) is applied for load balancing. Next, the data security is verified in the IDS training set, in which the features are extracted from preprocessed data. Then, the Synthetic Minority Oversampling Technique (SMOTE) is utilized for data balancing, and LWS-BiOLSTM is implemented to classify attacks. Furthermore, the attacked data is blocked, and non-attacked data is stored in the ICS through digital signature verification. Thus, the experimental results of the proposed framework outperform the other conventional techniques by achieving 98.78 % accuracy and 98.71 % security level.