XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset

Jul 16, 2026

Mechanistic interpretability under explainable AI (XAI) is leveraged to improve reliability of UAV intrusion detection on the UAVIDS-2025 tabular dataset. Tree ensembles, deep neural networks, hybrid stacking, and recent neural ensemble approaches are trained with stratified 10-fold cross validation, selecting XGBoost as top performer. SHAP supports global and local feature importance to explain attack-specific behavior and misclassifications. Violin plots and kernel density estimates visualize feature distributions, while bandwidth-optimized KDEs and the Westfall-Young permutation test quantify Density Support Intersection using Jensen-Shannon distances.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

Introduction

Machine Learning-Based UAVIDS

Methodology

Data Collection

Data Pre-Processing

XAI and Statistical Analysis for Reliable Intrusion Detection in the UAVIDS-2025 Dataset: From Tree to Hybrid and Tabular DNN Ensembles Iakovos-Christos Zarkadis University of Piraeus Athens, Greece [iakovos.zarkadis@gmail.com](iakovos.zarkadis@gmail.com) Christos Douligeris Dept. of Informatics University of Piraeus Piraeus, Greece [cdoulig@unipi.gr](cdoulig@unipi.gr) 10 Jul 2026 Abstract—During the last few years, the term Mechanistic Interpretability, a specific area, under the umbrella of explainable artificial intelligence (XAI), has been introduced, to explain the decisions made by complex machine learning (ML) models in critical systems like UAV intrusion detection systems (UAVIDS). In this paper, we apply best-practices for data pre-processing and examine a wide range of tree-ensembles, deep neural networks, hybrid stacking models and the latest ensemble neural networks to detect intrusions in UAV, with stratified 10-fold cross validation. With our top-performing model, XGBoost, we proceed to Shapley Additive explanations (SHAP), to analyze the global and local feature importances and understand which features, each attack targets, to mimic normal traffic and where the misclassifications occur. Furthermore a distribution analysis follows, by visually comparing violin plots and the curves of kernel density estimations. With the Westfall-Young permutation test for multiple comparisons, the Bandwidth optimization of the KDEs and the selection of Jensen-Shannon Distance for the arXiv :2605 . 13922v2 dataset. Index Terms—Machine learning (ML), explainable artificial intelligence (XAI), unmanned aerial vehicle network intrusion detection systems (UAVIDS), deep neural networks (DNN), Shapley Additive explanation (SHAP). I. INTRODUCTION Explainable techniques have gained recently everyone’s attention, due to their diversity and wide area of application. UAV intrusion detection, has gathered the attention of the research society for it’s many applications and dangers, that may occur in IoT networks in combination with the rise of 6G networks and their AI integration [2],[13],[19] . XAI methods, such as SHAP, LIME, Grad-CAM have been implemented in research papers, regarding UAV and IoT intrusion detection [5], [8], [11], [12], [14] . Methods like these, have been applied, for a great variety of algorithmic families, such as, Tree-based models, like Decision and Extra trees [1], [20], ensemble models, like XGBoost, LightGBM [9], [11], [12], neural networks and deep learning, like MLP, RNN, CNN, LSTM [24] . Due to the critical role of IoT networks, many frameworks have been designed, that combine deep, ensemble and federated learning to enhance intrusion detection [3],[23] . Modern frameworks direct their focus in explainability of predictions, of different modalities and models [5], [14], [21],[26], [28],[29] . Other newer frameworks focus on explainable Agentic AI [27] . Our focus in this paper, is first, to apply best pre-processing practices to ensure high data-quality, to have reliable, faithful and explainable results that provide deep insight about our data’s true nature. We apply a great variety of, well known, state-of-the-art tree-ensembles, like XGBoost [20], LightGBM, Histogram-Based Gradient Boosting, Random Forest, hybrid ensembles that combine linear, tree and bayesian models [10], deep neural networks, like RealMLP and deep neural network ensembles, like Ensemble-RealMLP, from some of the latest frameworks, such as AutoGluon and PyTabKit, designed specifically for tabular data [4], [15] . After we select our best classifier, XGBoost, we proceed to explainable techniques, with SHAP [22], like local and global feature importances, in order to analyze how his internal mechanism makes predictions and optimize his decisions. Next we examine the shape of our data, through Box-Plots, per attack, but also their densities and distribution shapes, with violin and Kernel Density Estimations [25],

FAQs

What is the main objective of the study on UAVIDS-2025?

To build reliable intrusion detection models for UAV networks and provide explainability and statistical evidence using XAI and distribution-based analysis.

Which models and validation strategy are used to detect intrusions?

A range of tree ensembles, deep neural networks, hybrid stacking models, and ensemble neural networks are evaluated using stratified 10-fold cross validation, with XGBoost selected as the top-performing classifier.

How does the paper explain model decisions and analyze feature behavior?

After training, SHAP is used for global and local feature importances to understand attack-targeted features and where misclassifications occur. Distribution analysis then uses violin plots and kernel density estimations, supported by bandwidth optimization.

Jul 16, 2026

Upload by Olivia Brown