Sign in Subscribe
Machine learning

Researchers Develop Novel Blockchain Architecture for Secure Drone Communications

Strategic Insights

— 1 min read

Researchers at INTI International University have developed a novel three-layer blockchain architecture, dubbed 3L-BC, designed to enhance security and privacy in unmanned aerial vehicle (UAV) communications through collaborative machine learning. The system, which was inspired by the need to address challenges faced by UAVs, including data confidentiality breaches, single points of failure, and computational resource constraints, strategically partitions functionality across three layers: the Drone Layer, the Fog Layer, and the blockchain layer.

Key Takeaways:

  • The 3L-BC architecture achieves higher throughput (5700 transactions per second (TPS)), reduced latency (0.2567 s), shorter processing time (0.475 s), and superior accuracy (99.98%) compared to existing systems.
  • Comprehensive threat modeling confirms the system's resilience against eavesdropping, tampering, model poisoning, and consensus attacks.
  • The architecture is particularly suitable for mission-critical applications in resource-constrained environments due to its balance between security requirements and computational efficiency.
  • The system's real-world applicability spans disaster response, precision agriculture, smart city traffic management, and infrastructure inspection.
  • 3L-BC's integration of blockchain and collaborative learning advances the frontier of secure, resource-aware, and privacy-preserving frameworks for dynamic drone networks.
  • The authors, Khang Wen Goh, Burhan Ul Islam Khan, Abdul Raouf Khan, Dwi Sudarno Putra, Suresh Sankaranarayanan, and Md. Alamin Bhuyian, have developed a trust-based fusor node selection mechanism to govern global model fusion.
  • The research was funded by the Deanship of Scientific Research, King Faisal University.

Statistics:

  • The 3L-BC architecture achieves a throughput of 5700 transactions per second (TPS).
  • The system has a latency of 0.2567 s and a processing time of 0.475 s.
  • The accuracy of the system is 99.98%.
  • The system's real-world applicability spans four different domains: disaster response, precision agriculture, smart city traffic management, and infrastructure inspection.

Sources:

  • NewsRx. Researchers from INTI International University Report Recent Findings in Machine Learning (3L-BC: a three-layer blockchain architecture for collaborative machine learning in secure drone communications). Journal of Engineering. October 20, 2025; p 3469.
  • 3L-BC: a three-layer blockchain architecture for collaborative machine learning in secure drone communications. Journal of King Saud University: Computer and Information Sciences, 2025, 37(8): 1-41.
  • Journal of King Saud University: Computer and Information Sciences - http://www.journals.elsevier.com/journal-of-king-saud-university-computer-and-information-sciences/

Read more