Blockchain-driven trust management and AI computing for sensor networks optimization

Area of Science:

• Computer Science
• Artificial Intelligence
• Network Security

Background:

• Intelligent systems rely on the Internet of Things (IoT) and edge computing for data processing.
• Existing security approaches face challenges like data eavesdropping in dynamic environments.
• Developing trustworthy and authenticated systems is crucial for smart system growth.

Purpose of the Study:

• To introduce a lightweight, trusted AI-driven model for enhancing security in complex systems.
• To ensure a more robust and reliable data-forwarding path.
• To address the research challenge of trustworthiness in dynamic IoT environments.

Main Methods:

• An adaptive technique explores network conditions for efficient data-transfer policies.
• Distributed, collaborative interactions enable load balancing across devices with minimal resources.
• Trust is continuously updated using real-time parameters and neighbor communication records.

Main Results:

• The proposed model enhances security and ensures a robust data-forwarding path.
• Distributed interactions improve system response time through load balancing.
• Continuous trust updates provide fault tolerance and trusted communication channels.

Conclusions:

• The AI-driven model offers superior security and reliability for intelligent systems.
• The approach is validated through simulations, demonstrating effectiveness in realistic scenarios.
• This research contributes to developing more trustworthy and authenticated connected systems.