Authors: Debasmita Dey, Nirnay Ghosh

Published on: March 07, 2024

Impact Score: 7.6

Arxiv code: Arxiv:2403.04416

Summary

• What is new: The introduction of iTRPL, a novel framework integrating trust and multi-agent reinforcement learning (MARL) into RPL for distinguishing between honest and malicious nodes.
• Why this is important: RPL’s vulnerability to insider attacks in IoT networks.
• What the research proposes: iTRPL framework uses trust computations and MARL for autonomous decision-making to improve security in IoT networks.
• Results: The simulation demonstrates that iTRPL can learn to make optimal decisions over time, effectively improving the security against insider threats.

Technical Details

Technological frameworks used: iTRPL, incorporating trust mechanisms and multi-agent reinforcement learning (MARL) into RPL

Models used: $\\epsilon$-Greedy MARL

Data used: Simulated behavior data of nodes in IoT networks

Potential Impact

IoT network providers, smart device manufacturers, healthcare technology companies, and industries relying on secure IoT communication could benefit or need to adapt.

Want to implement this idea in a business?

We have generated a startup concept here: TrustLayer.