Neutrosophic Intelligence for Secure UAV Communication: A Machine Learning Framework for Uncertainty-Aware Link Classification

Abstract

 Ensuring secure and reliable communication among unmanned aerial vehicles (UAVs) is a critical 
challenge in modern wireless networks, especially as drones are increasingly deployed in dynamic, 
adversarial, and mission-critical environments. This paper introduces a novel framework that leverages 
neutrosophic logic to model the truth (T), indeterminacy (I), and falsity (F) of UAV communication links, 
providing a mathematically robust approach to capture uncertainty and risk in real time. By integrating 
these neutrosophic values as features for advanced machine learning models—including XGBoost, deep 
neural networks (DNN), and hybrid architectures—the proposed system achieves high accuracy, 
adaptability, and explainability in classifying secure versus insecure links. The framework further 
incorporates online learning for real-time adaptation and SHAP-based explainability to enhance 
transparency in decision-making. Comparative evaluations demonstrate that neutrosophic-based 
modeling outperforms traditional fuzzy and binary approaches, particularly under noisy and uncertain 
conditions. The results are validated through both simulated and real-world datasets, confirming the 
practical relevance and robustness of the approach. This work positions neutrosophic logic, in synergy with 
machine learning and explainable AI, as a powerful foundation for next-generation secure UAV 
communication systems and aligns with recent advances in physical-layer security, and privacy-preserving 
protocols in UAV networks. 

DOI: 10.5281/zenodo.15873425