Enhancing UAV Security Through Zero Trust Architecture: An Advanced Deep Learning and Explainable AI Analysis

TL;DR

This work addresses UAV security by arguing for a Zero Trust Architecture that continuously authenticates all network entities using a deep neural network trained on RF signal representations. It integrates explainable AI tools (SHAP and LIME) to enhance transparency and accountability in UAV classifications within the ZTA framework. Empirically, the RF-based UAV detector achieves around $84.59$ accuracy, with PCA reducing feature dimensionality to 688 and cutting compute time, while preserving or improving key metrics like recall and F1. The study demonstrates the practical value of combining ZTA with DL and XAI for secure, interpretable UAV operations, and discusses limitations related to dataset scope and the potential for anomaly detection to handle unknown drone types in real-world deployments.

Abstract

In the dynamic and ever-changing domain of Unmanned Aerial Vehicles (UAVs), the utmost importance lies in guaranteeing resilient and lucid security measures. This study highlights the necessity of implementing a Zero Trust Architecture (ZTA) to enhance the security of unmanned aerial vehicles (UAVs), hence departing from conventional perimeter defences that may expose vulnerabilities. The Zero Trust Architecture (ZTA) paradigm requires a rigorous and continuous process of authenticating all network entities and communications. The accuracy of our methodology in detecting and identifying unmanned aerial vehicles (UAVs) is 84.59\%. This is achieved by utilizing Radio Frequency (RF) signals within a Deep Learning framework, a unique method. Precise identification is crucial in Zero Trust Architecture (ZTA), as it determines network access. In addition, the use of eXplainable Artificial Intelligence (XAI) tools such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) contributes to the improvement of the model's transparency and interpretability. Adherence to Zero Trust Architecture (ZTA) standards guarantees that the classifications of unmanned aerial vehicles (UAVs) are verifiable and comprehensible, enhancing security within the UAV field.

Figures (5)

• Figure 1: Continuous Authentication Workflow
• Figure 2: Illustration of the Interpretable AI Framework for Advanced Classification of UAVs.
• Figure 3: Confusion Matrix for Drone Classification
• Figure 4: SHAP summary plot
• Figure 5: Explaining individual prediction of deep learning classifier using LIME.