Blockchain-Based Smart Home Networks Security Empowered with Fused Machine Learning.

Area of Science:

• Cybersecurity
• Artificial Intelligence
• Internet of Things (IoT)

Background:

• Internet of Things (IoT) networks face significant security and privacy challenges due to their vast scale and deployment.
• Decentralized protection and privacy can be supported by blockchain-based solutions.
• Smart home networks require robust intrusion detection systems to safeguard user data and privacy.

Purpose of the Study:

• To propose a private blockchain-based smart home network architecture for intrusion detection.
• To investigate the implementation of a Fused Real-Time Sequential Deep Extreme Learning Machine (RTS-DELM) for detecting malicious activities in smart homes.
• To enhance intrusion detection accuracy through data fusion and decision-level fusion techniques.

Main Methods:

• Development of a private blockchain-based network architecture for smart homes.
• Implementation of a Fused Real-Time Sequential Deep Extreme Learning Machine (RTS-DELM) system model.
• Application of data fusion and decision-level fusion techniques for improved accuracy.

Main Results:

• The Fused RTS-DELM technique demonstrates significant stability and a low error rate in detecting intrusion activities.
• The proposed system effectively optimizes smart home networks for monitoring and detecting harmful or intrusive activities.
• Simulation findings validate the efficacy of the suggested technique in enhancing smart home security.

Conclusions:

• The proposed blockchain-based smart home network with Fused RTS-DELM offers a robust solution for intrusion detection.
• The integration of blockchain and advanced machine learning enhances the security and privacy of IoT environments.
• This approach provides a stable and accurate method for identifying and mitigating threats in smart home networks.