An artificial intelligence lightweight blockchain security model for security and privacy in IIoT systems.

Area of Science:

• Computer Science
• Cybersecurity
• Artificial Intelligence

Background:

• Industrial Internet of Things (IIoT) systems offer innovative business models but face significant security vulnerabilities, including privacy breaches, data integrity issues, and lack of trust.
• Traditional IIoT architectures struggle with centralized security and network intrusions, necessitating advanced protection mechanisms for cloud and edge computing environments.

Purpose of the Study:

• To implement an Artificial Intelligence-based Lightweight Blockchain Security Model (AILBSM) for enhanced privacy and security in Industrial Internet of Things (IIoT) systems.
• To address the security and privacy challenges inherent in cloud-based and edge computing IIoT deployments.

Main Methods:

• The research proposes a novel AILBSM framework combining lightweight blockchain technology with Convivial Optimized Sprinter Neural Network (COSNN) based AI.
• Features are transformed into encoded data using an Authentic Intrinsic Analysis (AIA) model to mitigate the impact of attacks.
• The model integrates auto-encoder based transformation and blockchain authentication for robust anomaly detection.

Main Results:

• The AILBSM framework achieved a minimized execution time of 0.6 seconds.
• Overall classification accuracy was improved to 99.8%, and detection performance reached 99.7%.
• The proposed model demonstrated significantly improved anomaly detection performance compared to existing techniques.

Conclusions:

• The AILBSM framework effectively enhances the security and privacy of Industrial Internet of Things (IIoT) systems.
• The integration of AI and blockchain provides a robust solution for protecting IIoT data in cloud and edge environments.
• The model's superior performance in accuracy, detection, and execution time validates its efficacy.